Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang...
Transcript of Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang...
![Page 1: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/1.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Lecture 13: Some Important ContinuousProbability Distributions (Part 2)
Katerina Stanková
Statistics (MAT1003)
May 14, 2012
![Page 2: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/2.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Outline
1 Erlang distributionFormulationApplication of Erlang distributionGamma distribution
2 Various Exercises
3 Chi-squared distributionBasicsApplicationsExamples
book: Sections 6.2-6.4,6.6
![Page 3: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/3.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
And now . . .
1 Erlang distributionFormulationApplication of Erlang distributionGamma distribution
2 Various Exercises
3 Chi-squared distributionBasicsApplicationsExamples
![Page 4: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/4.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Formulation
What is Erlang PDF?Let X1, X2, . . . Xn be IID exponentially distributed RV’s with parameter λ. Thenthe RV X def
= X1 + X2 + . . .+ Xn has an Erlang distribution with parameters nand λ, X ∼ Erl(n, λ),
f (x) =
{λn xn−1
(n−1)!exp(−λ x), x > 0,
0, elsewhere
![Page 5: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/5.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Formulation
What is Erlang PDF?Let X1, X2, . . . Xn be IID exponentially distributed RV’s with parameter λ. Thenthe RV X def
= X1 + X2 + . . .+ Xn has an Erlang distribution with parameters nand λ, X ∼ Erl(n, λ),
f (x) =
{λn xn−1
(n−1)!exp(−λ x), x > 0,
0, elsewhere
![Page 6: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/6.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Formulation
What is Erlang PDF?Let X1, X2, . . . Xn be IID exponentially distributed RV’s with parameter λ. Thenthe RV X def
= X1 + X2 + . . .+ Xn has an Erlang distribution with parameters nand λ, X ∼ Erl(n, λ),
f (x) =
{λn xn−1
(n−1)!exp(−λ x), x > 0,
0, elsewhere
![Page 7: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/7.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Formulation
What is Erlang PDF?Let X1, X2, . . . Xn be IID exponentially distributed RV’s with parameter λ. Thenthe RV X def
= X1 + X2 + . . .+ Xn has an Erlang distribution with parameters nand λ, X ∼ Erl(n, λ),
f (x) =
{λn xn−1
(n−1)!exp(−λ x), x > 0,
0, elsewhere
![Page 8: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/8.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Application of Erlang distribution
In a Poisson process the sum of n interarrival times has an Erlang distributionwith parameters n and λ
Example 5(c) (from before)
Suppose on average 6 people call some service number per minute. What isthe probability that it takes at least one minute for 3 people to call?
Z = 3 interarrival times
Z ∼ Erl(3, 18)
(λ = 18 for 3−minute time-unit)
P(Z ≥ 13
)
=
∫ ∞13
λn xn−1
(n − 1)!exp(−λ x) dx =
∫ ∞13
183 · x2
2!exp(−18 x) dx
=
[183
2·(− 1
18
)x2 exp(−18 x)
]∞x= 1
3
+183
2
∫ ∞13
218
x exp(−18 x) dx =[−162 x2 exp(−18 x)
]∞x= 1
3
+
[324 · (− 1
18) x exp(−18 x)
]∞x= 1
3
+ 18∫ ∞
13
exp(−18 x) dx
= [18 exp(−6) + 6 exp(−6)− exp(−18 x)]∞x= 13≈ 0.0620
![Page 9: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/9.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Application of Erlang distribution
In a Poisson process the sum of n interarrival times has an Erlang distributionwith parameters n and λ
Example 5(c) (from before)
Suppose on average 6 people call some service number per minute. What isthe probability that it takes at least one minute for 3 people to call?
Z = 3 interarrival times
Z ∼ Erl(3, 18)
(λ = 18 for 3−minute time-unit)
P(Z ≥ 13
)
=
∫ ∞13
λn xn−1
(n − 1)!exp(−λ x) dx =
∫ ∞13
183 · x2
2!exp(−18 x) dx
=
[183
2·(− 1
18
)x2 exp(−18 x)
]∞x= 1
3
+183
2
∫ ∞13
218
x exp(−18 x) dx =[−162 x2 exp(−18 x)
]∞x= 1
3
+
[324 · (− 1
18) x exp(−18 x)
]∞x= 1
3
+ 18∫ ∞
13
exp(−18 x) dx
= [18 exp(−6) + 6 exp(−6)− exp(−18 x)]∞x= 13≈ 0.0620
![Page 10: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/10.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Application of Erlang distribution
In a Poisson process the sum of n interarrival times has an Erlang distributionwith parameters n and λ
Example 5(c) (from before)
Suppose on average 6 people call some service number per minute. What isthe probability that it takes at least one minute for 3 people to call?
Z = 3 interarrival times
Z ∼ Erl(3, 18)
(λ = 18 for 3−minute time-unit)
P(Z ≥ 13
)
=
∫ ∞13
λn xn−1
(n − 1)!exp(−λ x) dx =
∫ ∞13
183 · x2
2!exp(−18 x) dx
=
[183
2·(− 1
18
)x2 exp(−18 x)
]∞x= 1
3
+183
2
∫ ∞13
218
x exp(−18 x) dx =[−162 x2 exp(−18 x)
]∞x= 1
3
+
[324 · (− 1
18) x exp(−18 x)
]∞x= 1
3
+ 18∫ ∞
13
exp(−18 x) dx
= [18 exp(−6) + 6 exp(−6)− exp(−18 x)]∞x= 13≈ 0.0620
![Page 11: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/11.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Application of Erlang distribution
In a Poisson process the sum of n interarrival times has an Erlang distributionwith parameters n and λ
Example 5(c) (from before)
Suppose on average 6 people call some service number per minute. What isthe probability that it takes at least one minute for 3 people to call?
Z = 3 interarrival times
Z ∼ Erl(3, 18)
(λ = 18 for 3−minute time-unit)
P(Z ≥ 13
)
=
∫ ∞13
λn xn−1
(n − 1)!exp(−λ x) dx =
∫ ∞13
183 · x2
2!exp(−18 x) dx
=
[183
2·(− 1
18
)x2 exp(−18 x)
]∞x= 1
3
+183
2
∫ ∞13
218
x exp(−18 x) dx =[−162 x2 exp(−18 x)
]∞x= 1
3
+
[324 · (− 1
18) x exp(−18 x)
]∞x= 1
3
+ 18∫ ∞
13
exp(−18 x) dx
= [18 exp(−6) + 6 exp(−6)− exp(−18 x)]∞x= 13≈ 0.0620
![Page 12: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/12.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Application of Erlang distribution
In a Poisson process the sum of n interarrival times has an Erlang distributionwith parameters n and λ
Example 5(c) (from before)
Suppose on average 6 people call some service number per minute. What isthe probability that it takes at least one minute for 3 people to call?
Z = 3 interarrival times
Z ∼ Erl(3, 18)
(λ = 18 for 3−minute time-unit)
P(Z ≥ 13
)
=
∫ ∞13
λn xn−1
(n − 1)!exp(−λ x) dx =
∫ ∞13
183 · x2
2!exp(−18 x) dx
=
[183
2·(− 1
18
)x2 exp(−18 x)
]∞x= 1
3
+183
2
∫ ∞13
218
x exp(−18 x) dx =[−162 x2 exp(−18 x)
]∞x= 1
3
+
[324 · (− 1
18) x exp(−18 x)
]∞x= 1
3
+ 18∫ ∞
13
exp(−18 x) dx
= [18 exp(−6) + 6 exp(−6)− exp(−18 x)]∞x= 13≈ 0.0620
![Page 13: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/13.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Application of Erlang distribution
In a Poisson process the sum of n interarrival times has an Erlang distributionwith parameters n and λ
Example 5(c) (from before)
Suppose on average 6 people call some service number per minute. What isthe probability that it takes at least one minute for 3 people to call?
Z = 3 interarrival times
Z ∼ Erl(3, 18) (λ = 18 for 3−minute time-unit)
P(Z ≥ 13
)
=
∫ ∞13
λn xn−1
(n − 1)!exp(−λ x) dx =
∫ ∞13
183 · x2
2!exp(−18 x) dx
=
[183
2·(− 1
18
)x2 exp(−18 x)
]∞x= 1
3
+183
2
∫ ∞13
218
x exp(−18 x) dx =[−162 x2 exp(−18 x)
]∞x= 1
3
+
[324 · (− 1
18) x exp(−18 x)
]∞x= 1
3
+ 18∫ ∞
13
exp(−18 x) dx
= [18 exp(−6) + 6 exp(−6)− exp(−18 x)]∞x= 13≈ 0.0620
![Page 14: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/14.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Application of Erlang distribution
In a Poisson process the sum of n interarrival times has an Erlang distributionwith parameters n and λ
Example 5(c) (from before)
Suppose on average 6 people call some service number per minute. What isthe probability that it takes at least one minute for 3 people to call?
Z = 3 interarrival times
Z ∼ Erl(3, 18) (λ = 18 for 3−minute time-unit)
P(Z ≥ 13
)
=
∫ ∞13
λn xn−1
(n − 1)!exp(−λ x) dx =
∫ ∞13
183 · x2
2!exp(−18 x) dx
=
[183
2·(− 1
18
)x2 exp(−18 x)
]∞x= 1
3
+183
2
∫ ∞13
218
x exp(−18 x) dx =[−162 x2 exp(−18 x)
]∞x= 1
3
+
[324 · (− 1
18) x exp(−18 x)
]∞x= 1
3
+ 18∫ ∞
13
exp(−18 x) dx
= [18 exp(−6) + 6 exp(−6)− exp(−18 x)]∞x= 13≈ 0.0620
![Page 15: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/15.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Application of Erlang distribution
In a Poisson process the sum of n interarrival times has an Erlang distributionwith parameters n and λ
Example 5(c) (from before)
Suppose on average 6 people call some service number per minute. What isthe probability that it takes at least one minute for 3 people to call?
Z = 3 interarrival times
Z ∼ Erl(3, 18) (λ = 18 for 3−minute time-unit)
P(Z ≥ 13
) =
∫ ∞13
λn xn−1
(n − 1)!exp(−λ x) dx
=
∫ ∞13
183 · x2
2!exp(−18 x) dx
=
[183
2·(− 1
18
)x2 exp(−18 x)
]∞x= 1
3
+183
2
∫ ∞13
218
x exp(−18 x) dx =[−162 x2 exp(−18 x)
]∞x= 1
3
+
[324 · (− 1
18) x exp(−18 x)
]∞x= 1
3
+ 18∫ ∞
13
exp(−18 x) dx
= [18 exp(−6) + 6 exp(−6)− exp(−18 x)]∞x= 13≈ 0.0620
![Page 16: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/16.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Application of Erlang distribution
In a Poisson process the sum of n interarrival times has an Erlang distributionwith parameters n and λ
Example 5(c) (from before)
Suppose on average 6 people call some service number per minute. What isthe probability that it takes at least one minute for 3 people to call?
Z = 3 interarrival times
Z ∼ Erl(3, 18) (λ = 18 for 3−minute time-unit)
P(Z ≥ 13
) =
∫ ∞13
λn xn−1
(n − 1)!exp(−λ x) dx =
∫ ∞13
183 · x2
2!exp(−18 x) dx
=
[183
2·(− 1
18
)x2 exp(−18 x)
]∞x= 1
3
+183
2
∫ ∞13
218
x exp(−18 x) dx =[−162 x2 exp(−18 x)
]∞x= 1
3
+
[324 · (− 1
18) x exp(−18 x)
]∞x= 1
3
+ 18∫ ∞
13
exp(−18 x) dx
= [18 exp(−6) + 6 exp(−6)− exp(−18 x)]∞x= 13≈ 0.0620
![Page 17: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/17.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Application of Erlang distribution
In a Poisson process the sum of n interarrival times has an Erlang distributionwith parameters n and λ
Example 5(c) (from before)
Suppose on average 6 people call some service number per minute. What isthe probability that it takes at least one minute for 3 people to call?
Z = 3 interarrival times
Z ∼ Erl(3, 18) (λ = 18 for 3−minute time-unit)
P(Z ≥ 13
) =
∫ ∞13
λn xn−1
(n − 1)!exp(−λ x) dx =
∫ ∞13
183 · x2
2!exp(−18 x) dx
=
[183
2·(− 1
18
)x2 exp(−18 x)
]∞x= 1
3
+183
2
∫ ∞13
218
x exp(−18 x) dx =[−162 x2 exp(−18 x)
]∞x= 1
3
+
[324 · (− 1
18) x exp(−18 x)
]∞x= 1
3
+ 18∫ ∞
13
exp(−18 x) dx
= [18 exp(−6) + 6 exp(−6)− exp(−18 x)]∞x= 13≈ 0.0620
![Page 18: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/18.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Application of Erlang distribution
In a Poisson process the sum of n interarrival times has an Erlang distributionwith parameters n and λ
Example 5(c) (from before)
Suppose on average 6 people call some service number per minute. What isthe probability that it takes at least one minute for 3 people to call?
Z = 3 interarrival times
Z ∼ Erl(3, 18) (λ = 18 for 3−minute time-unit)
P(Z ≥ 13
) =
∫ ∞13
λn xn−1
(n − 1)!exp(−λ x) dx =
∫ ∞13
183 · x2
2!exp(−18 x) dx
=
[183
2·(− 1
18
)x2 exp(−18 x)
]∞x= 1
3
+183
2
∫ ∞13
218
x exp(−18 x) dx =[−162 x2 exp(−18 x)
]∞x= 1
3
+
[324 · (− 1
18) x exp(−18 x)
]∞x= 1
3
+ 18∫ ∞
13
exp(−18 x) dx
= [18 exp(−6) + 6 exp(−6)− exp(−18 x)]∞x= 13≈ 0.0620
![Page 19: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/19.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Application of Erlang distribution
In a Poisson process the sum of n interarrival times has an Erlang distributionwith parameters n and λ
Example 5(c) (from before)
Suppose on average 6 people call some service number per minute. What isthe probability that it takes at least one minute for 3 people to call?
Z = 3 interarrival times
Z ∼ Erl(3, 18) (λ = 18 for 3−minute time-unit)
P(Z ≥ 13
) =
∫ ∞13
λn xn−1
(n − 1)!exp(−λ x) dx =
∫ ∞13
183 · x2
2!exp(−18 x) dx
=
[183
2·(− 1
18
)x2 exp(−18 x)
]∞x= 1
3
+183
2
∫ ∞13
218
x exp(−18 x) dx =[−162 x2 exp(−18 x)
]∞x= 1
3
+
[324 · (− 1
18) x exp(−18 x)
]∞x= 1
3
+ 18∫ ∞
13
exp(−18 x) dx
= [18 exp(−6) + 6 exp(−6)− exp(−18 x)]∞x= 13
≈ 0.0620
![Page 20: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/20.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Application of Erlang distribution
In a Poisson process the sum of n interarrival times has an Erlang distributionwith parameters n and λ
Example 5(c) (from before)
Suppose on average 6 people call some service number per minute. What isthe probability that it takes at least one minute for 3 people to call?
Z = 3 interarrival times
Z ∼ Erl(3, 18) (λ = 18 for 3−minute time-unit)
P(Z ≥ 13
) =
∫ ∞13
λn xn−1
(n − 1)!exp(−λ x) dx =
∫ ∞13
183 · x2
2!exp(−18 x) dx
=
[183
2·(− 1
18
)x2 exp(−18 x)
]∞x= 1
3
+183
2
∫ ∞13
218
x exp(−18 x) dx =[−162 x2 exp(−18 x)
]∞x= 1
3
+
[324 · (− 1
18) x exp(−18 x)
]∞x= 1
3
+ 18∫ ∞
13
exp(−18 x) dx
= [18 exp(−6) + 6 exp(−6)− exp(−18 x)]∞x= 13≈ 0.0620
![Page 21: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/21.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Gamma distribution
Derivation
One can prove that
(n − 1)!
=
∫ ∞0
tn−1 exp(−t) d t
Define the so-called Gamma-function:
Γ(α)def=
∫ ∞0
tα−1 exp(−t) dt for α ∈ R
Thenf (x) =λα xα−1
Γ(α)exp(−λ x) for x > 0 and 0 elsewhere
is a PDF. An RV with such a PDF has so-called Gamma distribution withparameters α and λ, X ∼ Γ(λ, α)(Plug in n = 1 or α = 1 to obtain the exponential distribution)
![Page 22: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/22.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Gamma distribution
DerivationOne can prove that
(n − 1)!
=
∫ ∞0
tn−1 exp(−t) d t
Define the so-called Gamma-function:
Γ(α)def=
∫ ∞0
tα−1 exp(−t) dt for α ∈ R
Thenf (x) =λα xα−1
Γ(α)exp(−λ x) for x > 0 and 0 elsewhere
is a PDF. An RV with such a PDF has so-called Gamma distribution withparameters α and λ, X ∼ Γ(λ, α)(Plug in n = 1 or α = 1 to obtain the exponential distribution)
![Page 23: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/23.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Gamma distribution
DerivationOne can prove that
(n − 1)! =
∫ ∞0
tn−1 exp(−t) d t
Define the so-called Gamma-function:
Γ(α)def=
∫ ∞0
tα−1 exp(−t) dt for α ∈ R
Thenf (x) =λα xα−1
Γ(α)exp(−λ x) for x > 0 and 0 elsewhere
is a PDF. An RV with such a PDF has so-called Gamma distribution withparameters α and λ, X ∼ Γ(λ, α)(Plug in n = 1 or α = 1 to obtain the exponential distribution)
![Page 24: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/24.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Gamma distribution
DerivationOne can prove that
(n − 1)! =
∫ ∞0
tn−1 exp(−t) d t
Define the so-called Gamma-function:
Γ(α)def=
∫ ∞0
tα−1 exp(−t) dt for α ∈ R
Thenf (x) =λα xα−1
Γ(α)exp(−λ x) for x > 0 and 0 elsewhere
is a PDF. An RV with such a PDF has so-called Gamma distribution withparameters α and λ, X ∼ Γ(λ, α)(Plug in n = 1 or α = 1 to obtain the exponential distribution)
![Page 25: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/25.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Gamma distribution
DerivationOne can prove that
(n − 1)! =
∫ ∞0
tn−1 exp(−t) d t
Define the so-called Gamma-function:
Γ(α)def=
∫ ∞0
tα−1 exp(−t) dt for α ∈ R
Thenf (x) =λα xα−1
Γ(α)exp(−λ x) for x > 0 and 0 elsewhere
is a PDF. An RV with such a PDF has so-called Gamma distribution withparameters α and λ, X ∼ Γ(λ, α)(Plug in n = 1 or α = 1 to obtain the exponential distribution)
![Page 26: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/26.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Gamma distribution
DerivationOne can prove that
(n − 1)! =
∫ ∞0
tn−1 exp(−t) d t
Define the so-called Gamma-function:
Γ(α)def=
∫ ∞0
tα−1 exp(−t) dt for α ∈ R
Thenf (x) =λα xα−1
Γ(α)exp(−λ x) for x > 0 and 0 elsewhere
is a PDF. An RV with such a PDF has so-called Gamma distribution withparameters α and λ, X ∼ Γ(λ, α)
(Plug in n = 1 or α = 1 to obtain the exponential distribution)
![Page 27: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/27.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Gamma distribution
DerivationOne can prove that
(n − 1)! =
∫ ∞0
tn−1 exp(−t) d t
Define the so-called Gamma-function:
Γ(α)def=
∫ ∞0
tα−1 exp(−t) dt for α ∈ R
Thenf (x) =λα xα−1
Γ(α)exp(−λ x) for x > 0 and 0 elsewhere
is a PDF. An RV with such a PDF has so-called Gamma distribution withparameters α and λ, X ∼ Γ(λ, α)(Plug in n = 1 or α = 1 to obtain the exponential distribution)
![Page 28: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/28.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
And now . . .
1 Erlang distributionFormulationApplication of Erlang distributionGamma distribution
2 Various Exercises
3 Chi-squared distributionBasicsApplicationsExamples
![Page 29: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/29.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(a) What is the probability that the net weight of a pack is at least 500grams?P(X ≥ 500) = P(Z ≥ 500−µ
σ= 500−505
5 = −1)= 1− P(Z ≤ −1) = 1− 0.1587 = 0.8413
(b) What is the probability that the gross weight of a pack is between 510and 520 grams? A : gross weight of a pack
A = X + Y ∼ N(µX + µY ,
√σ2
X + σ2Y
)= N
(505 + 10,
√52 + 12
)= N
(515,
√26)⇒ Z =
A− 515√26
∼ N (0, 1)
P(510− 515√
26≤ Z ≤ 520− 515√
26) = P(Z ≤ 0.98)− P(Z ≤ −0.98)
= 0.6730
![Page 30: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/30.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(a) What is the probability that the net weight of a pack is at least 500grams?P(X ≥ 500) = P(Z ≥ 500−µ
σ= 500−505
5 = −1)= 1− P(Z ≤ −1) = 1− 0.1587 = 0.8413
(b) What is the probability that the gross weight of a pack is between 510and 520 grams? A : gross weight of a pack
A = X + Y ∼ N(µX + µY ,
√σ2
X + σ2Y
)= N
(505 + 10,
√52 + 12
)= N
(515,
√26)⇒ Z =
A− 515√26
∼ N (0, 1)
P(510− 515√
26≤ Z ≤ 520− 515√
26) = P(Z ≤ 0.98)− P(Z ≤ −0.98)
= 0.6730
![Page 31: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/31.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(a) What is the probability that the net weight of a pack is at least 500grams?
P(X ≥ 500) = P(Z ≥ 500−µσ
= 500−5055 = −1)
= 1− P(Z ≤ −1) = 1− 0.1587 = 0.8413
(b) What is the probability that the gross weight of a pack is between 510and 520 grams? A : gross weight of a pack
A = X + Y ∼ N(µX + µY ,
√σ2
X + σ2Y
)= N
(505 + 10,
√52 + 12
)= N
(515,
√26)⇒ Z =
A− 515√26
∼ N (0, 1)
P(510− 515√
26≤ Z ≤ 520− 515√
26) = P(Z ≤ 0.98)− P(Z ≤ −0.98)
= 0.6730
![Page 32: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/32.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(a) What is the probability that the net weight of a pack is at least 500grams?
P(X ≥ 500) = P(Z ≥ 500−µσ
= 500−5055 = −1)
= 1− P(Z ≤ −1) = 1− 0.1587 = 0.8413
(b) What is the probability that the gross weight of a pack is between 510and 520 grams? A : gross weight of a pack
A = X + Y ∼ N(µX + µY ,
√σ2
X + σ2Y
)= N
(505 + 10,
√52 + 12
)= N
(515,
√26)⇒ Z =
A− 515√26
∼ N (0, 1)
P(510− 515√
26≤ Z ≤ 520− 515√
26) = P(Z ≤ 0.98)− P(Z ≤ −0.98)
= 0.6730
![Page 33: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/33.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(a) What is the probability that the net weight of a pack is at least 500grams?P(X ≥ 500) = P(Z ≥ 500−µ
σ= 500−505
5 = −1)
= 1− P(Z ≤ −1) = 1− 0.1587 = 0.8413
(b) What is the probability that the gross weight of a pack is between 510and 520 grams? A : gross weight of a pack
A = X + Y ∼ N(µX + µY ,
√σ2
X + σ2Y
)= N
(505 + 10,
√52 + 12
)= N
(515,
√26)⇒ Z =
A− 515√26
∼ N (0, 1)
P(510− 515√
26≤ Z ≤ 520− 515√
26) = P(Z ≤ 0.98)− P(Z ≤ −0.98)
= 0.6730
![Page 34: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/34.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(a) What is the probability that the net weight of a pack is at least 500grams?P(X ≥ 500) = P(Z ≥ 500−µ
σ= 500−505
5 = −1)= 1− P(Z ≤ −1) = 1− 0.1587 = 0.8413
(b) What is the probability that the gross weight of a pack is between 510and 520 grams? A : gross weight of a pack
A = X + Y ∼ N(µX + µY ,
√σ2
X + σ2Y
)= N
(505 + 10,
√52 + 12
)= N
(515,
√26)⇒ Z =
A− 515√26
∼ N (0, 1)
P(510− 515√
26≤ Z ≤ 520− 515√
26) = P(Z ≤ 0.98)− P(Z ≤ −0.98)
= 0.6730
![Page 35: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/35.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(a) What is the probability that the net weight of a pack is at least 500grams?P(X ≥ 500) = P(Z ≥ 500−µ
σ= 500−505
5 = −1)= 1− P(Z ≤ −1) = 1− 0.1587 = 0.8413
(b) What is the probability that the gross weight of a pack is between 510and 520 grams?
A : gross weight of a pack
A = X + Y ∼ N(µX + µY ,
√σ2
X + σ2Y
)= N
(505 + 10,
√52 + 12
)= N
(515,
√26)⇒ Z =
A− 515√26
∼ N (0, 1)
P(510− 515√
26≤ Z ≤ 520− 515√
26) = P(Z ≤ 0.98)− P(Z ≤ −0.98)
= 0.6730
![Page 36: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/36.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(a) What is the probability that the net weight of a pack is at least 500grams?P(X ≥ 500) = P(Z ≥ 500−µ
σ= 500−505
5 = −1)= 1− P(Z ≤ −1) = 1− 0.1587 = 0.8413
(b) What is the probability that the gross weight of a pack is between 510and 520 grams? A : gross weight of a pack
A = X + Y ∼ N(µX + µY ,
√σ2
X + σ2Y
)= N
(505 + 10,
√52 + 12
)= N
(515,
√26)⇒ Z =
A− 515√26
∼ N (0, 1)
P(510− 515√
26≤ Z ≤ 520− 515√
26) = P(Z ≤ 0.98)− P(Z ≤ −0.98)
= 0.6730
![Page 37: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/37.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(a) What is the probability that the net weight of a pack is at least 500grams?P(X ≥ 500) = P(Z ≥ 500−µ
σ= 500−505
5 = −1)= 1− P(Z ≤ −1) = 1− 0.1587 = 0.8413
(b) What is the probability that the gross weight of a pack is between 510and 520 grams? A : gross weight of a pack
A = X + Y
∼ N(µX + µY ,
√σ2
X + σ2Y
)= N
(505 + 10,
√52 + 12
)= N
(515,
√26)⇒ Z =
A− 515√26
∼ N (0, 1)
P(510− 515√
26≤ Z ≤ 520− 515√
26) = P(Z ≤ 0.98)− P(Z ≤ −0.98)
= 0.6730
![Page 38: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/38.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(a) What is the probability that the net weight of a pack is at least 500grams?P(X ≥ 500) = P(Z ≥ 500−µ
σ= 500−505
5 = −1)= 1− P(Z ≤ −1) = 1− 0.1587 = 0.8413
(b) What is the probability that the gross weight of a pack is between 510and 520 grams? A : gross weight of a pack
A = X + Y ∼ N(µX + µY ,
√σ2
X + σ2Y
)
= N(
505 + 10,√
52 + 12)
= N(
515,√
26)⇒ Z =
A− 515√26
∼ N (0, 1)
P(510− 515√
26≤ Z ≤ 520− 515√
26) = P(Z ≤ 0.98)− P(Z ≤ −0.98)
= 0.6730
![Page 39: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/39.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(a) What is the probability that the net weight of a pack is at least 500grams?P(X ≥ 500) = P(Z ≥ 500−µ
σ= 500−505
5 = −1)= 1− P(Z ≤ −1) = 1− 0.1587 = 0.8413
(b) What is the probability that the gross weight of a pack is between 510and 520 grams? A : gross weight of a pack
A = X + Y ∼ N(µX + µY ,
√σ2
X + σ2Y
)= N
(505 + 10,
√52 + 12
)
= N(
515,√
26)⇒ Z =
A− 515√26
∼ N (0, 1)
P(510− 515√
26≤ Z ≤ 520− 515√
26) = P(Z ≤ 0.98)− P(Z ≤ −0.98)
= 0.6730
![Page 40: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/40.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(a) What is the probability that the net weight of a pack is at least 500grams?P(X ≥ 500) = P(Z ≥ 500−µ
σ= 500−505
5 = −1)= 1− P(Z ≤ −1) = 1− 0.1587 = 0.8413
(b) What is the probability that the gross weight of a pack is between 510and 520 grams? A : gross weight of a pack
A = X + Y ∼ N(µX + µY ,
√σ2
X + σ2Y
)= N
(505 + 10,
√52 + 12
)= N
(515,
√26)
⇒ Z =A− 515√
26∼ N (0, 1)
P(510− 515√
26≤ Z ≤ 520− 515√
26) = P(Z ≤ 0.98)− P(Z ≤ −0.98)
= 0.6730
![Page 41: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/41.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(a) What is the probability that the net weight of a pack is at least 500grams?P(X ≥ 500) = P(Z ≥ 500−µ
σ= 500−505
5 = −1)= 1− P(Z ≤ −1) = 1− 0.1587 = 0.8413
(b) What is the probability that the gross weight of a pack is between 510and 520 grams? A : gross weight of a pack
A = X + Y ∼ N(µX + µY ,
√σ2
X + σ2Y
)= N
(505 + 10,
√52 + 12
)= N
(515,
√26)⇒ Z =
A− 515√26
∼ N (0, 1)
P(510− 515√
26≤ Z ≤ 520− 515√
26)
= P(Z ≤ 0.98)− P(Z ≤ −0.98)
= 0.6730
![Page 42: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/42.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(a) What is the probability that the net weight of a pack is at least 500grams?P(X ≥ 500) = P(Z ≥ 500−µ
σ= 500−505
5 = −1)= 1− P(Z ≤ −1) = 1− 0.1587 = 0.8413
(b) What is the probability that the gross weight of a pack is between 510and 520 grams? A : gross weight of a pack
A = X + Y ∼ N(µX + µY ,
√σ2
X + σ2Y
)= N
(505 + 10,
√52 + 12
)= N
(515,
√26)⇒ Z =
A− 515√26
∼ N (0, 1)
P(510− 515√
26≤ Z ≤ 520− 515√
26) = P(Z ≤ 0.98)− P(Z ≤ −0.98)
= 0.6730
![Page 43: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/43.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(a) What is the probability that the net weight of a pack is at least 500grams?P(X ≥ 500) = P(Z ≥ 500−µ
σ= 500−505
5 = −1)= 1− P(Z ≤ −1) = 1− 0.1587 = 0.8413
(b) What is the probability that the gross weight of a pack is between 510and 520 grams? A : gross weight of a pack
A = X + Y ∼ N(µX + µY ,
√σ2
X + σ2Y
)= N
(505 + 10,
√52 + 12
)= N
(515,
√26)⇒ Z =
A− 515√26
∼ N (0, 1)
P(510− 515√
26≤ Z ≤ 520− 515√
26) = P(Z ≤ 0.98)− P(Z ≤ −0.98)
= 0.6730
![Page 44: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/44.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(c) What is the probability that the gross weight of 10 packs is between5120 and 5170 grams? B : Gross weight of 10 packs,B =
∑10i=1(Xi + Yi ), with Xi ∼ N (505, 5), Yi ∼ N (10, 1)
B ∼ N (10µX + 10µY ,√
10σ2X + 10σ2
Y ) = N (5150,√
260)
⇒ Z = B−5150√260∼ N (0, 1)
P(5120 ≤ B ≤ 5170) = P(
5120− 5150√260
≤ Z ≤ 5170− 5150√260
)= P (−1.86 ≤ Z ≤ 1.24) = P (Z ≤ 1.24)− P (Z ≤ −1.86)
= 0.8925− 0.0314 = 0.8611
![Page 45: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/45.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(c) What is the probability that the gross weight of 10 packs is between5120 and 5170 grams? B : Gross weight of 10 packs,B =
∑10i=1(Xi + Yi ), with Xi ∼ N (505, 5), Yi ∼ N (10, 1)
B ∼ N (10µX + 10µY ,√
10σ2X + 10σ2
Y ) = N (5150,√
260)
⇒ Z = B−5150√260∼ N (0, 1)
P(5120 ≤ B ≤ 5170) = P(
5120− 5150√260
≤ Z ≤ 5170− 5150√260
)= P (−1.86 ≤ Z ≤ 1.24) = P (Z ≤ 1.24)− P (Z ≤ −1.86)
= 0.8925− 0.0314 = 0.8611
![Page 46: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/46.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(c) What is the probability that the gross weight of 10 packs is between5120 and 5170 grams?
B : Gross weight of 10 packs,B =
∑10i=1(Xi + Yi ), with Xi ∼ N (505, 5), Yi ∼ N (10, 1)
B ∼ N (10µX + 10µY ,√
10σ2X + 10σ2
Y ) = N (5150,√
260)
⇒ Z = B−5150√260∼ N (0, 1)
P(5120 ≤ B ≤ 5170) = P(
5120− 5150√260
≤ Z ≤ 5170− 5150√260
)= P (−1.86 ≤ Z ≤ 1.24) = P (Z ≤ 1.24)− P (Z ≤ −1.86)
= 0.8925− 0.0314 = 0.8611
![Page 47: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/47.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(c) What is the probability that the gross weight of 10 packs is between5120 and 5170 grams? B : Gross weight of 10 packs,
B =∑10
i=1(Xi + Yi ), with Xi ∼ N (505, 5), Yi ∼ N (10, 1)
B ∼ N (10µX + 10µY ,√
10σ2X + 10σ2
Y ) = N (5150,√
260)
⇒ Z = B−5150√260∼ N (0, 1)
P(5120 ≤ B ≤ 5170) = P(
5120− 5150√260
≤ Z ≤ 5170− 5150√260
)= P (−1.86 ≤ Z ≤ 1.24) = P (Z ≤ 1.24)− P (Z ≤ −1.86)
= 0.8925− 0.0314 = 0.8611
![Page 48: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/48.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(c) What is the probability that the gross weight of 10 packs is between5120 and 5170 grams? B : Gross weight of 10 packs,B =
∑10i=1(Xi + Yi ), with Xi ∼ N (505, 5), Yi ∼ N (10, 1)
B ∼ N (10µX + 10µY ,√
10σ2X + 10σ2
Y ) = N (5150,√
260)
⇒ Z = B−5150√260∼ N (0, 1)
P(5120 ≤ B ≤ 5170) = P(
5120− 5150√260
≤ Z ≤ 5170− 5150√260
)= P (−1.86 ≤ Z ≤ 1.24) = P (Z ≤ 1.24)− P (Z ≤ −1.86)
= 0.8925− 0.0314 = 0.8611
![Page 49: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/49.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(c) What is the probability that the gross weight of 10 packs is between5120 and 5170 grams? B : Gross weight of 10 packs,B =
∑10i=1(Xi + Yi ), with Xi ∼ N (505, 5), Yi ∼ N (10, 1)
B ∼ N (10µX + 10µY ,√
10σ2X + 10σ2
Y ) = N (5150,√
260)
⇒ Z = B−5150√260∼ N (0, 1)
P(5120 ≤ B ≤ 5170) = P(
5120− 5150√260
≤ Z ≤ 5170− 5150√260
)= P (−1.86 ≤ Z ≤ 1.24) = P (Z ≤ 1.24)− P (Z ≤ −1.86)
= 0.8925− 0.0314 = 0.8611
![Page 50: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/50.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(c) What is the probability that the gross weight of 10 packs is between5120 and 5170 grams? B : Gross weight of 10 packs,B =
∑10i=1(Xi + Yi ), with Xi ∼ N (505, 5), Yi ∼ N (10, 1)
B ∼ N (10µX + 10µY ,√
10σ2X + 10σ2
Y ) = N (5150,√
260)
⇒ Z = B−5150√260∼ N (0, 1)
P(5120 ≤ B ≤ 5170) = P(
5120− 5150√260
≤ Z ≤ 5170− 5150√260
)= P (−1.86 ≤ Z ≤ 1.24) = P (Z ≤ 1.24)− P (Z ≤ −1.86)
= 0.8925− 0.0314 = 0.8611
![Page 51: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/51.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(c) What is the probability that the gross weight of 10 packs is between5120 and 5170 grams? B : Gross weight of 10 packs,B =
∑10i=1(Xi + Yi ), with Xi ∼ N (505, 5), Yi ∼ N (10, 1)
B ∼ N (10µX + 10µY ,√
10σ2X + 10σ2
Y ) = N (5150,√
260)
⇒ Z = B−5150√260∼ N (0, 1)
P(5120 ≤ B ≤ 5170) = P(
5120− 5150√260
≤ Z ≤ 5170− 5150√260
)= P (−1.86 ≤ Z ≤ 1.24) = P (Z ≤ 1.24)− P (Z ≤ −1.86)
= 0.8925− 0.0314 = 0.8611
![Page 52: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/52.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(c) What is the probability that the gross weight of 10 packs is between5120 and 5170 grams? B : Gross weight of 10 packs,B =
∑10i=1(Xi + Yi ), with Xi ∼ N (505, 5), Yi ∼ N (10, 1)
B ∼ N (10µX + 10µY ,√
10σ2X + 10σ2
Y ) = N (5150,√
260)
⇒ Z = B−5150√260∼ N (0, 1)
P(5120 ≤ B ≤ 5170)
= P(
5120− 5150√260
≤ Z ≤ 5170− 5150√260
)= P (−1.86 ≤ Z ≤ 1.24) = P (Z ≤ 1.24)− P (Z ≤ −1.86)
= 0.8925− 0.0314 = 0.8611
![Page 53: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/53.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(c) What is the probability that the gross weight of 10 packs is between5120 and 5170 grams? B : Gross weight of 10 packs,B =
∑10i=1(Xi + Yi ), with Xi ∼ N (505, 5), Yi ∼ N (10, 1)
B ∼ N (10µX + 10µY ,√
10σ2X + 10σ2
Y ) = N (5150,√
260)
⇒ Z = B−5150√260∼ N (0, 1)
P(5120 ≤ B ≤ 5170) = P(
5120− 5150√260
≤ Z ≤ 5170− 5150√260
)
= P (−1.86 ≤ Z ≤ 1.24) = P (Z ≤ 1.24)− P (Z ≤ −1.86)
= 0.8925− 0.0314 = 0.8611
![Page 54: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/54.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(c) What is the probability that the gross weight of 10 packs is between5120 and 5170 grams? B : Gross weight of 10 packs,B =
∑10i=1(Xi + Yi ), with Xi ∼ N (505, 5), Yi ∼ N (10, 1)
B ∼ N (10µX + 10µY ,√
10σ2X + 10σ2
Y ) = N (5150,√
260)
⇒ Z = B−5150√260∼ N (0, 1)
P(5120 ≤ B ≤ 5170) = P(
5120− 5150√260
≤ Z ≤ 5170− 5150√260
)= P (−1.86 ≤ Z ≤ 1.24)
= P (Z ≤ 1.24)− P (Z ≤ −1.86)
= 0.8925− 0.0314 = 0.8611
![Page 55: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/55.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(c) What is the probability that the gross weight of 10 packs is between5120 and 5170 grams? B : Gross weight of 10 packs,B =
∑10i=1(Xi + Yi ), with Xi ∼ N (505, 5), Yi ∼ N (10, 1)
B ∼ N (10µX + 10µY ,√
10σ2X + 10σ2
Y ) = N (5150,√
260)
⇒ Z = B−5150√260∼ N (0, 1)
P(5120 ≤ B ≤ 5170) = P(
5120− 5150√260
≤ Z ≤ 5170− 5150√260
)= P (−1.86 ≤ Z ≤ 1.24) = P (Z ≤ 1.24)− P (Z ≤ −1.86)
= 0.8925− 0.0314 = 0.8611
![Page 56: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/56.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(c) What is the probability that the gross weight of 10 packs is between5120 and 5170 grams? B : Gross weight of 10 packs,B =
∑10i=1(Xi + Yi ), with Xi ∼ N (505, 5), Yi ∼ N (10, 1)
B ∼ N (10µX + 10µY ,√
10σ2X + 10σ2
Y ) = N (5150,√
260)
⇒ Z = B−5150√260∼ N (0, 1)
P(5120 ≤ B ≤ 5170) = P(
5120− 5150√260
≤ Z ≤ 5170− 5150√260
)= P (−1.86 ≤ Z ≤ 1.24) = P (Z ≤ 1.24)− P (Z ≤ −1.86)
= 0.8925− 0.0314 = 0.8611
![Page 57: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/57.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(d) 80 % of the gross weight of the packs is heavier than a particularweight. What is that weight? A ∼ N (515,
√26)
P(A ≥ a) = 0.8. What is a? Consider Z = A−515√26∼ N (0, 1)
P(A ≥ a) = P(
Z ≥ a− 515√26
)= 0.8
⇒P(
Z ≤ a− 515√26
)= 0.2
But P (Z ≤ z) = 0.2 for z = −0.84Apparently a−515√
26= −0.84⇒ a = −0.84
√26 + 515 = 510.7
In general . . .
X ∼ N (µ, σ) and P(X ≤ x) = p, P(Z ≤ z = x−µ
σ
)= p
Look up z in table A3 and then calculate x = σ x + µ
![Page 58: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/58.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(d) 80 % of the gross weight of the packs is heavier than a particularweight. What is that weight? A ∼ N (515,
√26)
P(A ≥ a) = 0.8. What is a? Consider Z = A−515√26∼ N (0, 1)
P(A ≥ a) = P(
Z ≥ a− 515√26
)= 0.8
⇒P(
Z ≤ a− 515√26
)= 0.2
But P (Z ≤ z) = 0.2 for z = −0.84Apparently a−515√
26= −0.84⇒ a = −0.84
√26 + 515 = 510.7
In general . . .
X ∼ N (µ, σ) and P(X ≤ x) = p, P(Z ≤ z = x−µ
σ
)= p
Look up z in table A3 and then calculate x = σ x + µ
![Page 59: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/59.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(d) 80 % of the gross weight of the packs is heavier than a particularweight. What is that weight?
A ∼ N (515,√
26)P(A ≥ a) = 0.8. What is a? Consider Z = A−515√
26∼ N (0, 1)
P(A ≥ a) = P(
Z ≥ a− 515√26
)= 0.8
⇒P(
Z ≤ a− 515√26
)= 0.2
But P (Z ≤ z) = 0.2 for z = −0.84Apparently a−515√
26= −0.84⇒ a = −0.84
√26 + 515 = 510.7
In general . . .
X ∼ N (µ, σ) and P(X ≤ x) = p, P(Z ≤ z = x−µ
σ
)= p
Look up z in table A3 and then calculate x = σ x + µ
![Page 60: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/60.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(d) 80 % of the gross weight of the packs is heavier than a particularweight. What is that weight? A ∼ N (515,
√26)
P(A ≥ a) = 0.8. What is a? Consider Z = A−515√26∼ N (0, 1)
P(A ≥ a) = P(
Z ≥ a− 515√26
)= 0.8
⇒P(
Z ≤ a− 515√26
)= 0.2
But P (Z ≤ z) = 0.2 for z = −0.84Apparently a−515√
26= −0.84⇒ a = −0.84
√26 + 515 = 510.7
In general . . .
X ∼ N (µ, σ) and P(X ≤ x) = p, P(Z ≤ z = x−µ
σ
)= p
Look up z in table A3 and then calculate x = σ x + µ
![Page 61: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/61.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(d) 80 % of the gross weight of the packs is heavier than a particularweight. What is that weight? A ∼ N (515,
√26)
P(A ≥ a) = 0.8. What is a?
Consider Z = A−515√26∼ N (0, 1)
P(A ≥ a) = P(
Z ≥ a− 515√26
)= 0.8
⇒P(
Z ≤ a− 515√26
)= 0.2
But P (Z ≤ z) = 0.2 for z = −0.84Apparently a−515√
26= −0.84⇒ a = −0.84
√26 + 515 = 510.7
In general . . .
X ∼ N (µ, σ) and P(X ≤ x) = p, P(Z ≤ z = x−µ
σ
)= p
Look up z in table A3 and then calculate x = σ x + µ
![Page 62: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/62.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(d) 80 % of the gross weight of the packs is heavier than a particularweight. What is that weight? A ∼ N (515,
√26)
P(A ≥ a) = 0.8. What is a? Consider Z = A−515√26∼ N (0, 1)
P(A ≥ a) = P(
Z ≥ a− 515√26
)= 0.8
⇒P(
Z ≤ a− 515√26
)= 0.2
But P (Z ≤ z) = 0.2 for z = −0.84Apparently a−515√
26= −0.84⇒ a = −0.84
√26 + 515 = 510.7
In general . . .
X ∼ N (µ, σ) and P(X ≤ x) = p, P(Z ≤ z = x−µ
σ
)= p
Look up z in table A3 and then calculate x = σ x + µ
![Page 63: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/63.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(d) 80 % of the gross weight of the packs is heavier than a particularweight. What is that weight? A ∼ N (515,
√26)
P(A ≥ a) = 0.8. What is a? Consider Z = A−515√26∼ N (0, 1)
P(A ≥ a)
= P(
Z ≥ a− 515√26
)= 0.8
⇒P(
Z ≤ a− 515√26
)= 0.2
But P (Z ≤ z) = 0.2 for z = −0.84Apparently a−515√
26= −0.84⇒ a = −0.84
√26 + 515 = 510.7
In general . . .
X ∼ N (µ, σ) and P(X ≤ x) = p, P(Z ≤ z = x−µ
σ
)= p
Look up z in table A3 and then calculate x = σ x + µ
![Page 64: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/64.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(d) 80 % of the gross weight of the packs is heavier than a particularweight. What is that weight? A ∼ N (515,
√26)
P(A ≥ a) = 0.8. What is a? Consider Z = A−515√26∼ N (0, 1)
P(A ≥ a) = P(
Z ≥ a− 515√26
)= 0.8
⇒P(
Z ≤ a− 515√26
)= 0.2
But P (Z ≤ z) = 0.2 for z = −0.84Apparently a−515√
26= −0.84⇒ a = −0.84
√26 + 515 = 510.7
In general . . .
X ∼ N (µ, σ) and P(X ≤ x) = p, P(Z ≤ z = x−µ
σ
)= p
Look up z in table A3 and then calculate x = σ x + µ
![Page 65: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/65.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(d) 80 % of the gross weight of the packs is heavier than a particularweight. What is that weight? A ∼ N (515,
√26)
P(A ≥ a) = 0.8. What is a? Consider Z = A−515√26∼ N (0, 1)
P(A ≥ a) = P(
Z ≥ a− 515√26
)= 0.8
⇒P(
Z ≤ a− 515√26
)= 0.2
But P (Z ≤ z) = 0.2 for z = −0.84Apparently a−515√
26= −0.84⇒ a = −0.84
√26 + 515 = 510.7
In general . . .
X ∼ N (µ, σ) and P(X ≤ x) = p, P(Z ≤ z = x−µ
σ
)= p
Look up z in table A3 and then calculate x = σ x + µ
![Page 66: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/66.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(d) 80 % of the gross weight of the packs is heavier than a particularweight. What is that weight? A ∼ N (515,
√26)
P(A ≥ a) = 0.8. What is a? Consider Z = A−515√26∼ N (0, 1)
P(A ≥ a) = P(
Z ≥ a− 515√26
)= 0.8
⇒P(
Z ≤ a− 515√26
)= 0.2
But P (Z ≤ z) = 0.2 for z = −0.84
Apparently a−515√26
= −0.84⇒ a = −0.84√
26 + 515 = 510.7
In general . . .
X ∼ N (µ, σ) and P(X ≤ x) = p, P(Z ≤ z = x−µ
σ
)= p
Look up z in table A3 and then calculate x = σ x + µ
![Page 67: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/67.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(d) 80 % of the gross weight of the packs is heavier than a particularweight. What is that weight? A ∼ N (515,
√26)
P(A ≥ a) = 0.8. What is a? Consider Z = A−515√26∼ N (0, 1)
P(A ≥ a) = P(
Z ≥ a− 515√26
)= 0.8
⇒P(
Z ≤ a− 515√26
)= 0.2
But P (Z ≤ z) = 0.2 for z = −0.84Apparently a−515√
26= −0.84⇒ a = −0.84
√26 + 515 = 510.7
In general . . .
X ∼ N (µ, σ) and P(X ≤ x) = p, P(Z ≤ z = x−µ
σ
)= p
Look up z in table A3 and then calculate x = σ x + µ
![Page 68: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/68.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(d) 80 % of the gross weight of the packs is heavier than a particularweight. What is that weight? A ∼ N (515,
√26)
P(A ≥ a) = 0.8. What is a? Consider Z = A−515√26∼ N (0, 1)
P(A ≥ a) = P(
Z ≥ a− 515√26
)= 0.8
⇒P(
Z ≤ a− 515√26
)= 0.2
But P (Z ≤ z) = 0.2 for z = −0.84Apparently a−515√
26= −0.84⇒ a = −0.84
√26 + 515 = 510.7
In general . . .
X ∼ N (µ, σ) and P(X ≤ x) = p, P(Z ≤ z = x−µ
σ
)= p
Look up z in table A3 and then calculate x = σ x + µ
![Page 69: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/69.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(d) 80 % of the gross weight of the packs is heavier than a particularweight. What is that weight? A ∼ N (515,
√26)
P(A ≥ a) = 0.8. What is a? Consider Z = A−515√26∼ N (0, 1)
P(A ≥ a) = P(
Z ≥ a− 515√26
)= 0.8
⇒P(
Z ≤ a− 515√26
)= 0.2
But P (Z ≤ z) = 0.2 for z = −0.84Apparently a−515√
26= −0.84⇒ a = −0.84
√26 + 515 = 510.7
In general . . .
X ∼ N (µ, σ) and P(X ≤ x) = p, P(Z ≤ z = x−µ
σ
)= p
Look up z in table A3 and then calculate x = σ x + µ
![Page 70: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/70.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(d) 80 % of the gross weight of the packs is heavier than a particularweight. What is that weight? A ∼ N (515,
√26)
P(A ≥ a) = 0.8. What is a? Consider Z = A−515√26∼ N (0, 1)
P(A ≥ a) = P(
Z ≥ a− 515√26
)= 0.8
⇒P(
Z ≤ a− 515√26
)= 0.2
But P (Z ≤ z) = 0.2 for z = −0.84Apparently a−515√
26= −0.84⇒ a = −0.84
√26 + 515 = 510.7
In general . . .
X ∼ N (µ, σ) and P(X ≤ x) = p, P(Z ≤ z = x−µ
σ
)= p
Look up z in table A3 and then calculate x = σ x + µ
![Page 71: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/71.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(e) What is the probability that the difference of net weights of two packs islower or equal than two grams? X1,X2 ∼ N (505, 5)Q : P(|X1 − X2| ≤ 2) = P(−2 ≤ X1 − X2 ≤ 2)X2 ∼ N (µX1 − µX2 ), σX1−X2 =
√V (X1 − X2)
V (X1 − X2) = V (X1) + V (−X2) = 12 V (X1) + (−1)2 V (X2) =V (X1) + V (X2)
Hence X1 − X2 ∼ N (0,√σ2
X1+ σ2
X2) = N
(0,√
25 + 25)
= N(
0,√
50)
⇒ Z =(x1 − x2)− 0√
50∼ N (0, 1)
P (−2 ≤ X1 − X2 ≤ 2) = P(X1 − X2 ≤ 2)− P(X1 − X2 ≤ −2)
P(
Z ≤ 2−0√50
)− P
(Z ≤ −2−0√
50
)P (Z ≤ 0.28)− P (Z ≤ −0.28) = 0.6103− 0.3897 = 0.2206
![Page 72: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/72.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(e) What is the probability that the difference of net weights of two packs islower or equal than two grams? X1,X2 ∼ N (505, 5)Q : P(|X1 − X2| ≤ 2) = P(−2 ≤ X1 − X2 ≤ 2)X2 ∼ N (µX1 − µX2 ), σX1−X2 =
√V (X1 − X2)
V (X1 − X2) = V (X1) + V (−X2) = 12 V (X1) + (−1)2 V (X2) =V (X1) + V (X2)
Hence X1 − X2 ∼ N (0,√σ2
X1+ σ2
X2) = N
(0,√
25 + 25)
= N(
0,√
50)
⇒ Z =(x1 − x2)− 0√
50∼ N (0, 1)
P (−2 ≤ X1 − X2 ≤ 2) = P(X1 − X2 ≤ 2)− P(X1 − X2 ≤ −2)
P(
Z ≤ 2−0√50
)− P
(Z ≤ −2−0√
50
)P (Z ≤ 0.28)− P (Z ≤ −0.28) = 0.6103− 0.3897 = 0.2206
![Page 73: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/73.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(e) What is the probability that the difference of net weights of two packs islower or equal than two grams?
X1,X2 ∼ N (505, 5)Q : P(|X1 − X2| ≤ 2) = P(−2 ≤ X1 − X2 ≤ 2)X2 ∼ N (µX1 − µX2 ), σX1−X2 =
√V (X1 − X2)
V (X1 − X2) = V (X1) + V (−X2) = 12 V (X1) + (−1)2 V (X2) =V (X1) + V (X2)
Hence X1 − X2 ∼ N (0,√σ2
X1+ σ2
X2) = N
(0,√
25 + 25)
= N(
0,√
50)
⇒ Z =(x1 − x2)− 0√
50∼ N (0, 1)
P (−2 ≤ X1 − X2 ≤ 2) = P(X1 − X2 ≤ 2)− P(X1 − X2 ≤ −2)
P(
Z ≤ 2−0√50
)− P
(Z ≤ −2−0√
50
)P (Z ≤ 0.28)− P (Z ≤ −0.28) = 0.6103− 0.3897 = 0.2206
![Page 74: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/74.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(e) What is the probability that the difference of net weights of two packs islower or equal than two grams? X1,X2 ∼ N (505, 5)
Q : P(|X1 − X2| ≤ 2) = P(−2 ≤ X1 − X2 ≤ 2)X2 ∼ N (µX1 − µX2 ), σX1−X2 =
√V (X1 − X2)
V (X1 − X2) = V (X1) + V (−X2) = 12 V (X1) + (−1)2 V (X2) =V (X1) + V (X2)
Hence X1 − X2 ∼ N (0,√σ2
X1+ σ2
X2) = N
(0,√
25 + 25)
= N(
0,√
50)
⇒ Z =(x1 − x2)− 0√
50∼ N (0, 1)
P (−2 ≤ X1 − X2 ≤ 2) = P(X1 − X2 ≤ 2)− P(X1 − X2 ≤ −2)
P(
Z ≤ 2−0√50
)− P
(Z ≤ −2−0√
50
)P (Z ≤ 0.28)− P (Z ≤ −0.28) = 0.6103− 0.3897 = 0.2206
![Page 75: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/75.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(e) What is the probability that the difference of net weights of two packs islower or equal than two grams? X1,X2 ∼ N (505, 5)Q : P(|X1 − X2| ≤ 2) = P(−2 ≤ X1 − X2 ≤ 2)
X2 ∼ N (µX1 − µX2 ), σX1−X2 =√
V (X1 − X2)V (X1 − X2) = V (X1) + V (−X2) = 12 V (X1) + (−1)2 V (X2) =V (X1) + V (X2)
Hence X1 − X2 ∼ N (0,√σ2
X1+ σ2
X2) = N
(0,√
25 + 25)
= N(
0,√
50)
⇒ Z =(x1 − x2)− 0√
50∼ N (0, 1)
P (−2 ≤ X1 − X2 ≤ 2) = P(X1 − X2 ≤ 2)− P(X1 − X2 ≤ −2)
P(
Z ≤ 2−0√50
)− P
(Z ≤ −2−0√
50
)P (Z ≤ 0.28)− P (Z ≤ −0.28) = 0.6103− 0.3897 = 0.2206
![Page 76: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/76.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(e) What is the probability that the difference of net weights of two packs islower or equal than two grams? X1,X2 ∼ N (505, 5)Q : P(|X1 − X2| ≤ 2) = P(−2 ≤ X1 − X2 ≤ 2)X2 ∼ N (µX1 − µX2 ), σX1−X2 =
√V (X1 − X2)
V (X1 − X2) = V (X1) + V (−X2) = 12 V (X1) + (−1)2 V (X2) =V (X1) + V (X2)
Hence X1 − X2 ∼ N (0,√σ2
X1+ σ2
X2) = N
(0,√
25 + 25)
= N(
0,√
50)
⇒ Z =(x1 − x2)− 0√
50∼ N (0, 1)
P (−2 ≤ X1 − X2 ≤ 2) = P(X1 − X2 ≤ 2)− P(X1 − X2 ≤ −2)
P(
Z ≤ 2−0√50
)− P
(Z ≤ −2−0√
50
)P (Z ≤ 0.28)− P (Z ≤ −0.28) = 0.6103− 0.3897 = 0.2206
![Page 77: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/77.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(e) What is the probability that the difference of net weights of two packs islower or equal than two grams? X1,X2 ∼ N (505, 5)Q : P(|X1 − X2| ≤ 2) = P(−2 ≤ X1 − X2 ≤ 2)X2 ∼ N (µX1 − µX2 ), σX1−X2 =
√V (X1 − X2)
V (X1 − X2) = V (X1) + V (−X2) = 12 V (X1) + (−1)2 V (X2) =V (X1) + V (X2)
Hence X1 − X2 ∼ N (0,√σ2
X1+ σ2
X2) = N
(0,√
25 + 25)
= N(
0,√
50)
⇒ Z =(x1 − x2)− 0√
50∼ N (0, 1)
P (−2 ≤ X1 − X2 ≤ 2) = P(X1 − X2 ≤ 2)− P(X1 − X2 ≤ −2)
P(
Z ≤ 2−0√50
)− P
(Z ≤ −2−0√
50
)P (Z ≤ 0.28)− P (Z ≤ −0.28) = 0.6103− 0.3897 = 0.2206
![Page 78: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/78.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(e) What is the probability that the difference of net weights of two packs islower or equal than two grams? X1,X2 ∼ N (505, 5)Q : P(|X1 − X2| ≤ 2) = P(−2 ≤ X1 − X2 ≤ 2)X2 ∼ N (µX1 − µX2 ), σX1−X2 =
√V (X1 − X2)
V (X1 − X2) = V (X1) + V (−X2) = 12 V (X1) + (−1)2 V (X2) =V (X1) + V (X2)
Hence X1 − X2 ∼ N (0,√σ2
X1+ σ2
X2)
= N(
0,√
25 + 25)
= N(
0,√
50)
⇒ Z =(x1 − x2)− 0√
50∼ N (0, 1)
P (−2 ≤ X1 − X2 ≤ 2) = P(X1 − X2 ≤ 2)− P(X1 − X2 ≤ −2)
P(
Z ≤ 2−0√50
)− P
(Z ≤ −2−0√
50
)P (Z ≤ 0.28)− P (Z ≤ −0.28) = 0.6103− 0.3897 = 0.2206
![Page 79: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/79.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(e) What is the probability that the difference of net weights of two packs islower or equal than two grams? X1,X2 ∼ N (505, 5)Q : P(|X1 − X2| ≤ 2) = P(−2 ≤ X1 − X2 ≤ 2)X2 ∼ N (µX1 − µX2 ), σX1−X2 =
√V (X1 − X2)
V (X1 − X2) = V (X1) + V (−X2) = 12 V (X1) + (−1)2 V (X2) =V (X1) + V (X2)
Hence X1 − X2 ∼ N (0,√σ2
X1+ σ2
X2) = N
(0,√
25 + 25)
= N(
0,√
50)
⇒ Z =(x1 − x2)− 0√
50∼ N (0, 1)
P (−2 ≤ X1 − X2 ≤ 2) = P(X1 − X2 ≤ 2)− P(X1 − X2 ≤ −2)
P(
Z ≤ 2−0√50
)− P
(Z ≤ −2−0√
50
)P (Z ≤ 0.28)− P (Z ≤ −0.28) = 0.6103− 0.3897 = 0.2206
![Page 80: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/80.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(e) What is the probability that the difference of net weights of two packs islower or equal than two grams? X1,X2 ∼ N (505, 5)Q : P(|X1 − X2| ≤ 2) = P(−2 ≤ X1 − X2 ≤ 2)X2 ∼ N (µX1 − µX2 ), σX1−X2 =
√V (X1 − X2)
V (X1 − X2) = V (X1) + V (−X2) = 12 V (X1) + (−1)2 V (X2) =V (X1) + V (X2)
Hence X1 − X2 ∼ N (0,√σ2
X1+ σ2
X2) = N
(0,√
25 + 25)
= N(
0,√
50)
⇒ Z =(x1 − x2)− 0√
50∼ N (0, 1)
P (−2 ≤ X1 − X2 ≤ 2) = P(X1 − X2 ≤ 2)− P(X1 − X2 ≤ −2)
P(
Z ≤ 2−0√50
)− P
(Z ≤ −2−0√
50
)P (Z ≤ 0.28)− P (Z ≤ −0.28) = 0.6103− 0.3897 = 0.2206
![Page 81: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/81.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(e) What is the probability that the difference of net weights of two packs islower or equal than two grams? X1,X2 ∼ N (505, 5)Q : P(|X1 − X2| ≤ 2) = P(−2 ≤ X1 − X2 ≤ 2)X2 ∼ N (µX1 − µX2 ), σX1−X2 =
√V (X1 − X2)
V (X1 − X2) = V (X1) + V (−X2) = 12 V (X1) + (−1)2 V (X2) =V (X1) + V (X2)
Hence X1 − X2 ∼ N (0,√σ2
X1+ σ2
X2) = N
(0,√
25 + 25)
= N(
0,√
50)
⇒ Z =(x1 − x2)− 0√
50∼ N (0, 1)
P (−2 ≤ X1 − X2 ≤ 2) = P(X1 − X2 ≤ 2)− P(X1 − X2 ≤ −2)
P(
Z ≤ 2−0√50
)− P
(Z ≤ −2−0√
50
)P (Z ≤ 0.28)− P (Z ≤ −0.28) = 0.6103− 0.3897 = 0.2206
![Page 82: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/82.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(e) What is the probability that the difference of net weights of two packs islower or equal than two grams? X1,X2 ∼ N (505, 5)Q : P(|X1 − X2| ≤ 2) = P(−2 ≤ X1 − X2 ≤ 2)X2 ∼ N (µX1 − µX2 ), σX1−X2 =
√V (X1 − X2)
V (X1 − X2) = V (X1) + V (−X2) = 12 V (X1) + (−1)2 V (X2) =V (X1) + V (X2)
Hence X1 − X2 ∼ N (0,√σ2
X1+ σ2
X2) = N
(0,√
25 + 25)
= N(
0,√
50)
⇒ Z =(x1 − x2)− 0√
50∼ N (0, 1)
P (−2 ≤ X1 − X2 ≤ 2) = P(X1 − X2 ≤ 2)− P(X1 − X2 ≤ −2)
P(
Z ≤ 2−0√50
)− P
(Z ≤ −2−0√
50
)
P (Z ≤ 0.28)− P (Z ≤ −0.28) = 0.6103− 0.3897 = 0.2206
![Page 83: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/83.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Example 6 (from last Thursday)
The net weight of a pack of coffee (500 grams) is a normally distributed RVwith parameters µ = 505 grams and σ = 5 grams.
(e) What is the probability that the difference of net weights of two packs islower or equal than two grams? X1,X2 ∼ N (505, 5)Q : P(|X1 − X2| ≤ 2) = P(−2 ≤ X1 − X2 ≤ 2)X2 ∼ N (µX1 − µX2 ), σX1−X2 =
√V (X1 − X2)
V (X1 − X2) = V (X1) + V (−X2) = 12 V (X1) + (−1)2 V (X2) =V (X1) + V (X2)
Hence X1 − X2 ∼ N (0,√σ2
X1+ σ2
X2) = N
(0,√
25 + 25)
= N(
0,√
50)
⇒ Z =(x1 − x2)− 0√
50∼ N (0, 1)
P (−2 ≤ X1 − X2 ≤ 2) = P(X1 − X2 ≤ 2)− P(X1 − X2 ≤ −2)
P(
Z ≤ 2−0√50
)− P
(Z ≤ −2−0√
50
)P (Z ≤ 0.28)− P (Z ≤ −0.28) = 0.6103− 0.3897 = 0.2206
![Page 84: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/84.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Observation
Let Z ∼ N (0, 1). For cumulative density of the RV X = Z 2 we have:
F (x) = P(X ≤ x) = P(Z 2 ≤ x) = P(|z| ≤√
x) = P(−√
x ≤ Z ≤√x) = G(
√x)−G(−
√x)
where G is the cumulative density of Z . So
f (x) = F ′(x) = 12 x−
12 ·G′(
√x)− (− 1
2 )x−12 ·G′(−
√x)
= 12 x−
12 · 1√
2πexp(− x
2 ) + 12 x−
12 · 1√
2πexp(− x
2 )=x− 1
2 exp(− x2 )
4√π
Apparently: Γ( 12 ) =
√π and X = Z 2 has a Gamma-distribution with
parameters λ = 12 (β = 2) and α = 1
2
![Page 85: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/85.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Observation
Let Z ∼ N (0, 1). For cumulative density of the RV X = Z 2 we have:
F (x) = P(X ≤ x) = P(Z 2 ≤ x) = P(|z| ≤√
x) = P(−√
x ≤ Z ≤√x) = G(
√x)−G(−
√x)
where G is the cumulative density of Z . So
f (x) = F ′(x) = 12 x−
12 ·G′(
√x)− (− 1
2 )x−12 ·G′(−
√x)
= 12 x−
12 · 1√
2πexp(− x
2 ) + 12 x−
12 · 1√
2πexp(− x
2 )=x− 1
2 exp(− x2 )
4√π
Apparently: Γ( 12 ) =
√π and X = Z 2 has a Gamma-distribution with
parameters λ = 12 (β = 2) and α = 1
2
![Page 86: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/86.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Observation
Let Z ∼ N (0, 1). For cumulative density of the RV X = Z 2 we have:
F (x) = P(X ≤ x) = P(Z 2 ≤ x) = P(|z| ≤√
x) = P(−√
x ≤ Z ≤√x) = G(
√x)−G(−
√x)
where G is the cumulative density of Z . So
f (x) = F ′(x) = 12 x−
12 ·G′(
√x)− (− 1
2 )x−12 ·G′(−
√x)
= 12 x−
12 · 1√
2πexp(− x
2 ) + 12 x−
12 · 1√
2πexp(− x
2 )=x− 1
2 exp(− x2 )
4√π
Apparently: Γ( 12 ) =
√π and X = Z 2 has a Gamma-distribution with
parameters λ = 12 (β = 2) and α = 1
2
![Page 87: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/87.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Observation
Let Z ∼ N (0, 1). For cumulative density of the RV X = Z 2 we have:
F (x) = P(X ≤ x) = P(Z 2 ≤ x) = P(|z| ≤√
x) = P(−√
x ≤ Z ≤√x) = G(
√x)−G(−
√x)
where G is the cumulative density of Z . So
f (x) = F ′(x) = 12 x−
12 ·G′(
√x)− (− 1
2 )x−12 ·G′(−
√x)
= 12 x−
12 · 1√
2πexp(− x
2 ) + 12 x−
12 · 1√
2πexp(− x
2 )=x− 1
2 exp(− x2 )
4√π
Apparently: Γ( 12 ) =
√π and X = Z 2 has a Gamma-distribution with
parameters λ = 12 (β = 2) and α = 1
2
![Page 88: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/88.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Observation
Let Z ∼ N (0, 1). For cumulative density of the RV X = Z 2 we have:
F (x) = P(X ≤ x) = P(Z 2 ≤ x) = P(|z| ≤√
x) = P(−√
x ≤ Z ≤√x) = G(
√x)−G(−
√x)
where G is the cumulative density of Z . So
f (x) = F ′(x) = 12 x−
12 ·G′(
√x)− (− 1
2 )x−12 ·G′(−
√x)
= 12 x−
12 · 1√
2πexp(− x
2 ) + 12 x−
12 · 1√
2πexp(− x
2 )=x− 1
2 exp(− x2 )
4√π
Apparently: Γ( 12 ) =
√π and X = Z 2 has a Gamma-distribution with
parameters λ = 12 (β = 2) and α = 1
2
![Page 89: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/89.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Observation
Let Z ∼ N (0, 1). For cumulative density of the RV X = Z 2 we have:
F (x) = P(X ≤ x) = P(Z 2 ≤ x) = P(|z| ≤√
x) = P(−√
x ≤ Z ≤√x) = G(
√x)−G(−
√x)
where G is the cumulative density of Z . So
f (x) = F ′(x) = 12 x−
12 ·G′(
√x)− (− 1
2 )x−12 ·G′(−
√x)
= 12 x−
12 · 1√
2πexp(− x
2 ) + 12 x−
12 · 1√
2πexp(− x
2 )
=x− 1
2 exp(− x2 )
4√π
Apparently: Γ( 12 ) =
√π and X = Z 2 has a Gamma-distribution with
parameters λ = 12 (β = 2) and α = 1
2
![Page 90: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/90.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Observation
Let Z ∼ N (0, 1). For cumulative density of the RV X = Z 2 we have:
F (x) = P(X ≤ x) = P(Z 2 ≤ x) = P(|z| ≤√
x) = P(−√
x ≤ Z ≤√x) = G(
√x)−G(−
√x)
where G is the cumulative density of Z . So
f (x) = F ′(x) = 12 x−
12 ·G′(
√x)− (− 1
2 )x−12 ·G′(−
√x)
= 12 x−
12 · 1√
2πexp(− x
2 ) + 12 x−
12 · 1√
2πexp(− x
2 )=x− 1
2 exp(− x2 )
4√π
Apparently: Γ( 12 ) =
√π and X = Z 2 has a Gamma-distribution with
parameters λ = 12 (β = 2) and α = 1
2
![Page 91: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/91.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Observation
Let Z ∼ N (0, 1). For cumulative density of the RV X = Z 2 we have:
F (x) = P(X ≤ x) = P(Z 2 ≤ x) = P(|z| ≤√
x) = P(−√
x ≤ Z ≤√x) = G(
√x)−G(−
√x)
where G is the cumulative density of Z . So
f (x) = F ′(x) = 12 x−
12 ·G′(
√x)− (− 1
2 )x−12 ·G′(−
√x)
= 12 x−
12 · 1√
2πexp(− x
2 ) + 12 x−
12 · 1√
2πexp(− x
2 )=x− 1
2 exp(− x2 )
4√π
Apparently: Γ( 12 ) =
√π and X = Z 2 has a Gamma-distribution with
parameters λ = 12 (β = 2) and α = 1
2
![Page 92: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/92.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
And now . . .
1 Erlang distributionFormulationApplication of Erlang distributionGamma distribution
2 Various Exercises
3 Chi-squared distributionBasicsApplicationsExamples
![Page 93: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/93.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Basics
Formulation
If X1, X2, . . . , Xn are IID, Xi ∼ N (0, 1), then χ2 def= X 2
1 + X 22 + . . .+ X 2
n
has a Gamma-distribution with parameters α = n/2 and λ = 1/2(β = 2)
This distribution is also called a Chi-squared distribution with n degreesof freedom
Notation χ2 ∼ χ2n
Book: Table A5: X s.t. P(χ2 ≥ x) = α for several values of v (] degrees offreedom) and α
![Page 94: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/94.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Basics
Formulation
If X1, X2, . . . , Xn are IID, Xi ∼ N (0, 1), then χ2 def= X 2
1 + X 22 + . . .+ X 2
n
has a Gamma-distribution with parameters α = n/2 and λ = 1/2(β = 2)
This distribution is also called a Chi-squared distribution with n degreesof freedom
Notation χ2 ∼ χ2n
Book: Table A5: X s.t. P(χ2 ≥ x) = α for several values of v (] degrees offreedom) and α
![Page 95: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/95.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Basics
Formulation
If X1, X2, . . . , Xn are IID, Xi ∼ N (0, 1), then χ2 def= X 2
1 + X 22 + . . .+ X 2
n
has a Gamma-distribution with parameters α = n/2 and λ = 1/2(β = 2)
This distribution is also called a Chi-squared distribution with n degreesof freedom
Notation χ2 ∼ χ2n
Book: Table A5: X s.t. P(χ2 ≥ x) = α for several values of v (] degrees offreedom) and α
![Page 96: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/96.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Basics
Formulation
If X1, X2, . . . , Xn are IID, Xi ∼ N (0, 1), then χ2 def= X 2
1 + X 22 + . . .+ X 2
n
has a Gamma-distribution with parameters α = n/2 and λ = 1/2(β = 2)
This distribution is also called a Chi-squared distribution with n degreesof freedom
Notation χ2 ∼ χ2n
Book: Table A5: X s.t. P(χ2 ≥ x) = α for several values of v (] degrees offreedom) and α
![Page 97: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/97.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Basics
Formulation
If X1, X2, . . . , Xn are IID, Xi ∼ N (0, 1), then χ2 def= X 2
1 + X 22 + . . .+ X 2
n
has a Gamma-distribution with parameters α = n/2 and λ = 1/2(β = 2)
This distribution is also called a Chi-squared distribution with n degreesof freedom
Notation χ2 ∼ χ2n
Book: Table A5: X s.t. P(χ2 ≥ x) = α for several values of v (] degrees offreedom) and α
![Page 98: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/98.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Basics
Formulation
If X1, X2, . . . , Xn are IID, Xi ∼ N (0, 1), then χ2 def= X 2
1 + X 22 + . . .+ X 2
n
has a Gamma-distribution with parameters α = n/2 and λ = 1/2(β = 2)
This distribution is also called a Chi-squared distribution with n degreesof freedom
Notation χ2 ∼ χ2n
Book: Table A5: X s.t. P(χ2 ≥ x) = α for several values of v (] degrees offreedom) and α
![Page 99: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/99.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Applications
Estimation of σ
Let X1, X2, . . . , Xn ∼ N (µ, σ) IDD with known µ and unknown σ
Then Zi = Xi−µσ∼ N (0, 1)
⇒ Z 2i = (Xi−µ)2
σ2 ∼ χ2i
⇒ χ2 def=∑n
i=1 Z 2i = 1
σ2
∑ni=1(Xi − µ)2 ∼ χ2
n
![Page 100: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/100.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Applications
Estimation of σ
Let X1, X2, . . . , Xn ∼ N (µ, σ) IDD with known µ and unknown σ
Then Zi = Xi−µσ∼ N (0, 1)
⇒ Z 2i = (Xi−µ)2
σ2 ∼ χ2i
⇒ χ2 def=∑n
i=1 Z 2i = 1
σ2
∑ni=1(Xi − µ)2 ∼ χ2
n
![Page 101: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/101.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Applications
Estimation of σ
Let X1, X2, . . . , Xn ∼ N (µ, σ) IDD with known µ and unknown σThen Zi = Xi−µ
σ∼ N (0, 1)
⇒ Z 2i = (Xi−µ)2
σ2 ∼ χ2i
⇒ χ2 def=∑n
i=1 Z 2i = 1
σ2
∑ni=1(Xi − µ)2 ∼ χ2
n
![Page 102: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/102.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Applications
Estimation of σ
Let X1, X2, . . . , Xn ∼ N (µ, σ) IDD with known µ and unknown σThen Zi = Xi−µ
σ∼ N (0, 1)
⇒ Z 2i = (Xi−µ)2
σ2 ∼ χ2i
⇒ χ2 def=∑n
i=1 Z 2i = 1
σ2
∑ni=1(Xi − µ)2 ∼ χ2
n
![Page 103: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/103.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Applications
Estimation of σ
Let X1, X2, . . . , Xn ∼ N (µ, σ) IDD with known µ and unknown σThen Zi = Xi−µ
σ∼ N (0, 1)
⇒ Z 2i = (Xi−µ)2
σ2 ∼ χ2i
⇒ χ2 def=∑n
i=1 Z 2i = 1
σ2
∑ni=1(Xi − µ)2 ∼ χ2
n
![Page 104: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/104.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Examples
Example 7
Let X1, X2, . . . , Xn ∼ N (µ, σ) IDD with µ = 5 and unknown σ. Therealizations for X1, . . . , X5 are 3.5, 5.7, 1.2, 6.8, and 7.1. What values of σare reasonable?
Let χ2 def= 1
σ2
∑5i=1(Xi − µ)2
= 1σ2 ((−1.5)2 + (0.7)2 + (−3.8)2 + (1.8)2 + (2.1)2) = 24.83
σ2
Table A5: P(χ2 ≥ 12.832) = 0.025 and P(χ2 ≥ 0.831) = 0.975
So (fill the realization for χ2 :) P(0.831 ≤ 24.83σ2 ≤ 12.832) =
0.975− 0.025 = 0.95⇔ P(σ2 ∈ [1.935, 29.88]) = 0.95⇔ P(σ ∈ [1.391, 5.466]) = 0.95
Apparently reasonable values for σ are between 1.391 and 5.466. We call[1.391, 5.466] a 95 % confidence interval for σSimilarly, [1.935, 29.88] is a 95 % confidence interval for σ2
![Page 105: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/105.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Examples
Example 7
Let X1, X2, . . . , Xn ∼ N (µ, σ) IDD with µ = 5 and unknown σ. Therealizations for X1, . . . , X5 are 3.5, 5.7, 1.2, 6.8, and 7.1. What values of σare reasonable?
Let χ2 def= 1
σ2
∑5i=1(Xi − µ)2
= 1σ2 ((−1.5)2 + (0.7)2 + (−3.8)2 + (1.8)2 + (2.1)2) = 24.83
σ2
Table A5: P(χ2 ≥ 12.832) = 0.025 and P(χ2 ≥ 0.831) = 0.975
So (fill the realization for χ2 :) P(0.831 ≤ 24.83σ2 ≤ 12.832) =
0.975− 0.025 = 0.95⇔ P(σ2 ∈ [1.935, 29.88]) = 0.95⇔ P(σ ∈ [1.391, 5.466]) = 0.95
Apparently reasonable values for σ are between 1.391 and 5.466. We call[1.391, 5.466] a 95 % confidence interval for σSimilarly, [1.935, 29.88] is a 95 % confidence interval for σ2
![Page 106: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/106.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Examples
Example 7
Let X1, X2, . . . , Xn ∼ N (µ, σ) IDD with µ = 5 and unknown σ. Therealizations for X1, . . . , X5 are 3.5, 5.7, 1.2, 6.8, and 7.1. What values of σare reasonable?Let χ2 def
= 1σ2
∑5i=1(Xi − µ)2
= 1σ2 ((−1.5)2 + (0.7)2 + (−3.8)2 + (1.8)2 + (2.1)2) = 24.83
σ2
Table A5: P(χ2 ≥ 12.832) = 0.025 and P(χ2 ≥ 0.831) = 0.975
So (fill the realization for χ2 :) P(0.831 ≤ 24.83σ2 ≤ 12.832) =
0.975− 0.025 = 0.95⇔ P(σ2 ∈ [1.935, 29.88]) = 0.95⇔ P(σ ∈ [1.391, 5.466]) = 0.95
Apparently reasonable values for σ are between 1.391 and 5.466. We call[1.391, 5.466] a 95 % confidence interval for σSimilarly, [1.935, 29.88] is a 95 % confidence interval for σ2
![Page 107: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/107.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Examples
Example 7
Let X1, X2, . . . , Xn ∼ N (µ, σ) IDD with µ = 5 and unknown σ. Therealizations for X1, . . . , X5 are 3.5, 5.7, 1.2, 6.8, and 7.1. What values of σare reasonable?Let χ2 def
= 1σ2
∑5i=1(Xi − µ)2
= 1σ2 ((−1.5)2 + (0.7)2 + (−3.8)2 + (1.8)2 + (2.1)2) = 24.83
σ2
Table A5: P(χ2 ≥ 12.832) = 0.025 and P(χ2 ≥ 0.831) = 0.975
So (fill the realization for χ2 :) P(0.831 ≤ 24.83σ2 ≤ 12.832) =
0.975− 0.025 = 0.95⇔ P(σ2 ∈ [1.935, 29.88]) = 0.95⇔ P(σ ∈ [1.391, 5.466]) = 0.95
Apparently reasonable values for σ are between 1.391 and 5.466. We call[1.391, 5.466] a 95 % confidence interval for σSimilarly, [1.935, 29.88] is a 95 % confidence interval for σ2
![Page 108: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/108.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Examples
Example 7
Let X1, X2, . . . , Xn ∼ N (µ, σ) IDD with µ = 5 and unknown σ. Therealizations for X1, . . . , X5 are 3.5, 5.7, 1.2, 6.8, and 7.1. What values of σare reasonable?Let χ2 def
= 1σ2
∑5i=1(Xi − µ)2
= 1σ2 ((−1.5)2 + (0.7)2 + (−3.8)2 + (1.8)2 + (2.1)2) = 24.83
σ2
Table A5: P(χ2 ≥ 12.832) = 0.025 and P(χ2 ≥ 0.831) = 0.975
So (fill the realization for χ2 :) P(0.831 ≤ 24.83σ2 ≤ 12.832) =
0.975− 0.025 = 0.95⇔ P(σ2 ∈ [1.935, 29.88]) = 0.95⇔ P(σ ∈ [1.391, 5.466]) = 0.95
Apparently reasonable values for σ are between 1.391 and 5.466. We call[1.391, 5.466] a 95 % confidence interval for σSimilarly, [1.935, 29.88] is a 95 % confidence interval for σ2
![Page 109: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/109.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Examples
Example 7
Let X1, X2, . . . , Xn ∼ N (µ, σ) IDD with µ = 5 and unknown σ. Therealizations for X1, . . . , X5 are 3.5, 5.7, 1.2, 6.8, and 7.1. What values of σare reasonable?Let χ2 def
= 1σ2
∑5i=1(Xi − µ)2
= 1σ2 ((−1.5)2 + (0.7)2 + (−3.8)2 + (1.8)2 + (2.1)2) = 24.83
σ2
Table A5: P(χ2 ≥ 12.832) = 0.025 and P(χ2 ≥ 0.831) = 0.975
So (fill the realization for χ2 :) P(0.831 ≤ 24.83σ2 ≤ 12.832) =
0.975− 0.025 = 0.95⇔ P(σ2 ∈ [1.935, 29.88]) = 0.95
⇔ P(σ ∈ [1.391, 5.466]) = 0.95
Apparently reasonable values for σ are between 1.391 and 5.466. We call[1.391, 5.466] a 95 % confidence interval for σSimilarly, [1.935, 29.88] is a 95 % confidence interval for σ2
![Page 110: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/110.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Examples
Example 7
Let X1, X2, . . . , Xn ∼ N (µ, σ) IDD with µ = 5 and unknown σ. Therealizations for X1, . . . , X5 are 3.5, 5.7, 1.2, 6.8, and 7.1. What values of σare reasonable?Let χ2 def
= 1σ2
∑5i=1(Xi − µ)2
= 1σ2 ((−1.5)2 + (0.7)2 + (−3.8)2 + (1.8)2 + (2.1)2) = 24.83
σ2
Table A5: P(χ2 ≥ 12.832) = 0.025 and P(χ2 ≥ 0.831) = 0.975
So (fill the realization for χ2 :) P(0.831 ≤ 24.83σ2 ≤ 12.832) =
0.975− 0.025 = 0.95⇔ P(σ2 ∈ [1.935, 29.88]) = 0.95⇔ P(σ ∈ [1.391, 5.466]) = 0.95
Apparently reasonable values for σ are between 1.391 and 5.466. We call[1.391, 5.466] a 95 % confidence interval for σSimilarly, [1.935, 29.88] is a 95 % confidence interval for σ2
![Page 111: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/111.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Examples
Example 7
Let X1, X2, . . . , Xn ∼ N (µ, σ) IDD with µ = 5 and unknown σ. Therealizations for X1, . . . , X5 are 3.5, 5.7, 1.2, 6.8, and 7.1. What values of σare reasonable?Let χ2 def
= 1σ2
∑5i=1(Xi − µ)2
= 1σ2 ((−1.5)2 + (0.7)2 + (−3.8)2 + (1.8)2 + (2.1)2) = 24.83
σ2
Table A5: P(χ2 ≥ 12.832) = 0.025 and P(χ2 ≥ 0.831) = 0.975
So (fill the realization for χ2 :) P(0.831 ≤ 24.83σ2 ≤ 12.832) =
0.975− 0.025 = 0.95⇔ P(σ2 ∈ [1.935, 29.88]) = 0.95⇔ P(σ ∈ [1.391, 5.466]) = 0.95
Apparently reasonable values for σ are between 1.391 and 5.466. We call[1.391, 5.466] a 95 % confidence interval for σ
Similarly, [1.935, 29.88] is a 95 % confidence interval for σ2
![Page 112: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/112.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Examples
Example 7
Let X1, X2, . . . , Xn ∼ N (µ, σ) IDD with µ = 5 and unknown σ. Therealizations for X1, . . . , X5 are 3.5, 5.7, 1.2, 6.8, and 7.1. What values of σare reasonable?Let χ2 def
= 1σ2
∑5i=1(Xi − µ)2
= 1σ2 ((−1.5)2 + (0.7)2 + (−3.8)2 + (1.8)2 + (2.1)2) = 24.83
σ2
Table A5: P(χ2 ≥ 12.832) = 0.025 and P(χ2 ≥ 0.831) = 0.975
So (fill the realization for χ2 :) P(0.831 ≤ 24.83σ2 ≤ 12.832) =
0.975− 0.025 = 0.95⇔ P(σ2 ∈ [1.935, 29.88]) = 0.95⇔ P(σ ∈ [1.391, 5.466]) = 0.95
Apparently reasonable values for σ are between 1.391 and 5.466. We call[1.391, 5.466] a 95 % confidence interval for σSimilarly, [1.935, 29.88] is a 95 % confidence interval for σ2
![Page 113: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/113.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Examples
Example 8: What if µ is unknown as well?
Data: X1, X2, . . . , Xn ∼ N (µ, σ) IDD with µ, σ unknown.Some calculation show:
n∑i=1
(Xi − µ)2
=n∑
i=1
((xi − x) + (x − µ))2
=n∑
i=1
(xi − x)2 + 2n∑
i=1
(xi − x)(x − µ) +n∑
i=1
(x − µ)2
=n∑
i=1
(xi − x)2 + n · (x − µ)2
Now, since s2 = 1n−1
∑ni=1(xi − x)2, we have
1σ2
n∑i=1
(xi − µ)2
︸ ︷︷ ︸∼χ2
n
= (n−1)·s2
σ2 + (x−µ)2
σ2/n ⇒ X = 1n
∑ni=1 xi ∼ N (µ, σ√
n )
⇒ (X−µ)2
σ2/√
n =(
X−µσ/√
n
)2∼ χ2
1 ⇒ the statistics
χ2 = (n−1) s2
σ2 =∑n
i=1(xi−x)2
σ2 ∼ χ2n−1
![Page 114: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/114.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Examples
Example 8: What if µ is unknown as well?
Data: X1, X2, . . . , Xn ∼ N (µ, σ) IDD with µ, σ unknown.
Some calculation show:n∑
i=1
(Xi − µ)2
=n∑
i=1
((xi − x) + (x − µ))2
=n∑
i=1
(xi − x)2 + 2n∑
i=1
(xi − x)(x − µ) +n∑
i=1
(x − µ)2
=n∑
i=1
(xi − x)2 + n · (x − µ)2
Now, since s2 = 1n−1
∑ni=1(xi − x)2, we have
1σ2
n∑i=1
(xi − µ)2
︸ ︷︷ ︸∼χ2
n
= (n−1)·s2
σ2 + (x−µ)2
σ2/n ⇒ X = 1n
∑ni=1 xi ∼ N (µ, σ√
n )
⇒ (X−µ)2
σ2/√
n =(
X−µσ/√
n
)2∼ χ2
1 ⇒ the statistics
χ2 = (n−1) s2
σ2 =∑n
i=1(xi−x)2
σ2 ∼ χ2n−1
![Page 115: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/115.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Examples
Example 8: What if µ is unknown as well?
Data: X1, X2, . . . , Xn ∼ N (µ, σ) IDD with µ, σ unknown.Some calculation show:
n∑i=1
(Xi − µ)2
=n∑
i=1
((xi − x) + (x − µ))2
=n∑
i=1
(xi − x)2 + 2n∑
i=1
(xi − x)(x − µ) +n∑
i=1
(x − µ)2
=n∑
i=1
(xi − x)2 + n · (x − µ)2
Now, since s2 = 1n−1
∑ni=1(xi − x)2, we have
1σ2
n∑i=1
(xi − µ)2
︸ ︷︷ ︸∼χ2
n
= (n−1)·s2
σ2 + (x−µ)2
σ2/n ⇒ X = 1n
∑ni=1 xi ∼ N (µ, σ√
n )
⇒ (X−µ)2
σ2/√
n =(
X−µσ/√
n
)2∼ χ2
1 ⇒ the statistics
χ2 = (n−1) s2
σ2 =∑n
i=1(xi−x)2
σ2 ∼ χ2n−1
![Page 116: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/116.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Examples
Example 8: What if µ is unknown as well?
Data: X1, X2, . . . , Xn ∼ N (µ, σ) IDD with µ, σ unknown.Some calculation show:
n∑i=1
(Xi − µ)2 =n∑
i=1
((xi − x) + (x − µ))2
=n∑
i=1
(xi − x)2 + 2n∑
i=1
(xi − x)(x − µ) +n∑
i=1
(x − µ)2
=n∑
i=1
(xi − x)2 + n · (x − µ)2
Now, since s2 = 1n−1
∑ni=1(xi − x)2, we have
1σ2
n∑i=1
(xi − µ)2
︸ ︷︷ ︸∼χ2
n
= (n−1)·s2
σ2 + (x−µ)2
σ2/n ⇒ X = 1n
∑ni=1 xi ∼ N (µ, σ√
n )
⇒ (X−µ)2
σ2/√
n =(
X−µσ/√
n
)2∼ χ2
1 ⇒ the statistics
χ2 = (n−1) s2
σ2 =∑n
i=1(xi−x)2
σ2 ∼ χ2n−1
![Page 117: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/117.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Examples
Example 8: What if µ is unknown as well?
Data: X1, X2, . . . , Xn ∼ N (µ, σ) IDD with µ, σ unknown.Some calculation show:
n∑i=1
(Xi − µ)2 =n∑
i=1
((xi − x) + (x − µ))2
=n∑
i=1
(xi − x)2 + 2n∑
i=1
(xi − x)(x − µ) +n∑
i=1
(x − µ)2
=n∑
i=1
(xi − x)2 + n · (x − µ)2
Now, since s2 = 1n−1
∑ni=1(xi − x)2, we have
1σ2
n∑i=1
(xi − µ)2
︸ ︷︷ ︸∼χ2
n
= (n−1)·s2
σ2 + (x−µ)2
σ2/n ⇒ X = 1n
∑ni=1 xi ∼ N (µ, σ√
n )
⇒ (X−µ)2
σ2/√
n =(
X−µσ/√
n
)2∼ χ2
1 ⇒ the statistics
χ2 = (n−1) s2
σ2 =∑n
i=1(xi−x)2
σ2 ∼ χ2n−1
![Page 118: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/118.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Examples
Example 8: What if µ is unknown as well?
Data: X1, X2, . . . , Xn ∼ N (µ, σ) IDD with µ, σ unknown.Some calculation show:
n∑i=1
(Xi − µ)2 =n∑
i=1
((xi − x) + (x − µ))2
=n∑
i=1
(xi − x)2 + 2n∑
i=1
(xi − x)(x − µ) +n∑
i=1
(x − µ)2
=n∑
i=1
(xi − x)2 + n · (x − µ)2
Now, since s2 = 1n−1
∑ni=1(xi − x)2, we have
1σ2
n∑i=1
(xi − µ)2
︸ ︷︷ ︸∼χ2
n
= (n−1)·s2
σ2 + (x−µ)2
σ2/n ⇒ X = 1n
∑ni=1 xi ∼ N (µ, σ√
n )
⇒ (X−µ)2
σ2/√
n =(
X−µσ/√
n
)2∼ χ2
1 ⇒ the statistics
χ2 = (n−1) s2
σ2 =∑n
i=1(xi−x)2
σ2 ∼ χ2n−1
![Page 119: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/119.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Examples
Example 8: What if µ is unknown as well?
Data: X1, X2, . . . , Xn ∼ N (µ, σ) IDD with µ, σ unknown.Some calculation show:
n∑i=1
(Xi − µ)2 =n∑
i=1
((xi − x) + (x − µ))2
=n∑
i=1
(xi − x)2 + 2n∑
i=1
(xi − x)(x − µ) +n∑
i=1
(x − µ)2
=n∑
i=1
(xi − x)2 + n · (x − µ)2
Now, since s2 = 1n−1
∑ni=1(xi − x)2, we have
1σ2
n∑i=1
(xi − µ)2
︸ ︷︷ ︸∼χ2
n
= (n−1)·s2
σ2 + (x−µ)2
σ2/n ⇒ X = 1n
∑ni=1 xi ∼ N (µ, σ√
n )
⇒ (X−µ)2
σ2/√
n =(
X−µσ/√
n
)2∼ χ2
1 ⇒ the statistics
χ2 = (n−1) s2
σ2 =∑n
i=1(xi−x)2
σ2 ∼ χ2n−1
![Page 120: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/120.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Examples
Example 8: What if µ is unknown as well?
Data: X1, X2, . . . , Xn ∼ N (µ, σ) IDD with µ, σ unknown.Some calculation show:
n∑i=1
(Xi − µ)2 =n∑
i=1
((xi − x) + (x − µ))2
=n∑
i=1
(xi − x)2 + 2n∑
i=1
(xi − x)(x − µ) +n∑
i=1
(x − µ)2
=n∑
i=1
(xi − x)2 + n · (x − µ)2
Now, since s2 = 1n−1
∑ni=1(xi − x)2, we have
1σ2
n∑i=1
(xi − µ)2
︸ ︷︷ ︸∼χ2
n
= (n−1)·s2
σ2 + (x−µ)2
σ2/n
⇒ X = 1n
∑ni=1 xi ∼ N (µ, σ√
n )
⇒ (X−µ)2
σ2/√
n =(
X−µσ/√
n
)2∼ χ2
1 ⇒ the statistics
χ2 = (n−1) s2
σ2 =∑n
i=1(xi−x)2
σ2 ∼ χ2n−1
![Page 121: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/121.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Examples
Example 8: What if µ is unknown as well?
Data: X1, X2, . . . , Xn ∼ N (µ, σ) IDD with µ, σ unknown.Some calculation show:
n∑i=1
(Xi − µ)2 =n∑
i=1
((xi − x) + (x − µ))2
=n∑
i=1
(xi − x)2 + 2n∑
i=1
(xi − x)(x − µ) +n∑
i=1
(x − µ)2
=n∑
i=1
(xi − x)2 + n · (x − µ)2
Now, since s2 = 1n−1
∑ni=1(xi − x)2, we have
1σ2
n∑i=1
(xi − µ)2
︸ ︷︷ ︸∼χ2
n
= (n−1)·s2
σ2 + (x−µ)2
σ2/n ⇒ X = 1n
∑ni=1 xi ∼ N (µ, σ√
n )
⇒ (X−µ)2
σ2/√
n =(
X−µσ/√
n
)2∼ χ2
1 ⇒ the statistics
χ2 = (n−1) s2
σ2 =∑n
i=1(xi−x)2
σ2 ∼ χ2n−1
![Page 122: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/122.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Examples
Example 8: What if µ is unknown as well?
Data: X1, X2, . . . , Xn ∼ N (µ, σ) IDD with µ, σ unknown.Some calculation show:
n∑i=1
(Xi − µ)2 =n∑
i=1
((xi − x) + (x − µ))2
=n∑
i=1
(xi − x)2 + 2n∑
i=1
(xi − x)(x − µ) +n∑
i=1
(x − µ)2
=n∑
i=1
(xi − x)2 + n · (x − µ)2
Now, since s2 = 1n−1
∑ni=1(xi − x)2, we have
1σ2
n∑i=1
(xi − µ)2
︸ ︷︷ ︸∼χ2
n
= (n−1)·s2
σ2 + (x−µ)2
σ2/n ⇒ X = 1n
∑ni=1 xi ∼ N (µ, σ√
n )
⇒ (X−µ)2
σ2/√
n =(
X−µσ/√
n
)2∼ χ2
1 ⇒ the statistics
χ2 = (n−1) s2
σ2 =∑n
i=1(xi−x)2
σ2 ∼ χ2n−1
![Page 123: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/123.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Examples
Example 8: What if µ is unknown as well?
Data: X1, X2, . . . , Xn ∼ N (µ, σ) IDD with µ, σ unknown.Some calculation show:
n∑i=1
(Xi − µ)2 =n∑
i=1
((xi − x) + (x − µ))2
=n∑
i=1
(xi − x)2 + 2n∑
i=1
(xi − x)(x − µ) +n∑
i=1
(x − µ)2
=n∑
i=1
(xi − x)2 + n · (x − µ)2
Now, since s2 = 1n−1
∑ni=1(xi − x)2, we have
1σ2
n∑i=1
(xi − µ)2
︸ ︷︷ ︸∼χ2
n
= (n−1)·s2
σ2 + (x−µ)2
σ2/n ⇒ X = 1n
∑ni=1 xi ∼ N (µ, σ√
n )
⇒ (X−µ)2
σ2/√
n =(
X−µσ/√
n
)2∼ χ2
1
⇒ the statistics
χ2 = (n−1) s2
σ2 =∑n
i=1(xi−x)2
σ2 ∼ χ2n−1
![Page 124: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/124.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Examples
Example 8: What if µ is unknown as well?
Data: X1, X2, . . . , Xn ∼ N (µ, σ) IDD with µ, σ unknown.Some calculation show:
n∑i=1
(Xi − µ)2 =n∑
i=1
((xi − x) + (x − µ))2
=n∑
i=1
(xi − x)2 + 2n∑
i=1
(xi − x)(x − µ) +n∑
i=1
(x − µ)2
=n∑
i=1
(xi − x)2 + n · (x − µ)2
Now, since s2 = 1n−1
∑ni=1(xi − x)2, we have
1σ2
n∑i=1
(xi − µ)2
︸ ︷︷ ︸∼χ2
n
= (n−1)·s2
σ2 + (x−µ)2
σ2/n ⇒ X = 1n
∑ni=1 xi ∼ N (µ, σ√
n )
⇒ (X−µ)2
σ2/√
n =(
X−µσ/√
n
)2∼ χ2
1 ⇒ the statistics
χ2 = (n−1) s2
σ2 =∑n
i=1(xi−x)2
σ2 ∼ χ2n−1
![Page 125: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/125.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Examples
Example 8: What if µ is unknown as well?
Data: X1, X2, . . . , Xn ∼ N (µ, σ) IDD with µ, σ unknown.Some calculation show:
n∑i=1
(Xi − µ)2 =n∑
i=1
((xi − x) + (x − µ))2
=n∑
i=1
(xi − x)2 + 2n∑
i=1
(xi − x)(x − µ) +n∑
i=1
(x − µ)2
=n∑
i=1
(xi − x)2 + n · (x − µ)2
Now, since s2 = 1n−1
∑ni=1(xi − x)2, we have
1σ2
n∑i=1
(xi − µ)2
︸ ︷︷ ︸∼χ2
n
= (n−1)·s2
σ2 + (x−µ)2
σ2/n ⇒ X = 1n
∑ni=1 xi ∼ N (µ, σ√
n )
⇒ (X−µ)2
σ2/√
n =(
X−µσ/√
n
)2∼ χ2
1 ⇒ the statistics
χ2 = (n−1) s2
σ2 =∑n
i=1(xi−x)2
σ2 ∼ χ2n−1
![Page 126: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/126.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Examples
Example 7 (b)
Let X1, X2, . . . , Xn ∼ N (µ, σ) IDD with µ = 5 and unknown σ. The realizationsfor X1, . . . , X5 are 3.5, 5.7, 1.2, 6.8, and 7.1. What values of σ are reasonable
Let χ2 def= (n−1)s2
σ2 ∼ χ2n−1 = χ2
4
X = 15 (3.5 + 5.7 + 1.2 + 6.8 + 7.1) = 4.86
(n − 1)s2 =∑n
i=1(xi − x)2 = 24.732⇒ χ2 = 24.732
σ2
Construct a 95% confidence interval for σ :
Table A5: P(χ2 ≥ 11.143) = 0.025 and P(χ2 ≥ 0.484) = 0.975⇒ P(0.484 ≤ 24.732/σ2 ≤ 11.143) = 0.95⇒ P(24.732/11.143 ≤ σ2 ≤ 24.732/0.484) = 0.95
95% CI for σ2: [24.732/11.143, 24.732/0.484] = [0.220, 51.0999]95% CI for σ: [1.490, 7.148]
Important!: These calculations use the fact that Xis are normally distributed. Ifit is not the case, we cannot use χ2-distributions!
![Page 127: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/127.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Examples
Example 7 (b)
Let X1, X2, . . . , Xn ∼ N (µ, σ) IDD with µ = 5 and unknown σ. The realizationsfor X1, . . . , X5 are 3.5, 5.7, 1.2, 6.8, and 7.1. What values of σ are reasonable
Let χ2 def= (n−1)s2
σ2 ∼ χ2n−1 = χ2
4
X = 15 (3.5 + 5.7 + 1.2 + 6.8 + 7.1) = 4.86
(n − 1)s2 =∑n
i=1(xi − x)2 = 24.732⇒ χ2 = 24.732
σ2
Construct a 95% confidence interval for σ :
Table A5: P(χ2 ≥ 11.143) = 0.025 and P(χ2 ≥ 0.484) = 0.975⇒ P(0.484 ≤ 24.732/σ2 ≤ 11.143) = 0.95⇒ P(24.732/11.143 ≤ σ2 ≤ 24.732/0.484) = 0.95
95% CI for σ2: [24.732/11.143, 24.732/0.484] = [0.220, 51.0999]95% CI for σ: [1.490, 7.148]Important!: These calculations use the fact that Xis are normally distributed. Ifit is not the case, we cannot use χ2-distributions!
![Page 128: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/128.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Examples
Example 7 (b)
Let X1, X2, . . . , Xn ∼ N (µ, σ) IDD with µ = 5 and unknown σ. The realizationsfor X1, . . . , X5 are 3.5, 5.7, 1.2, 6.8, and 7.1. What values of σ are reasonableLet χ2 def
= (n−1)s2
σ2 ∼ χ2n−1 = χ2
4
X = 15 (3.5 + 5.7 + 1.2 + 6.8 + 7.1) = 4.86
(n − 1)s2 =∑n
i=1(xi − x)2 = 24.732⇒ χ2 = 24.732
σ2
Construct a 95% confidence interval for σ :
Table A5: P(χ2 ≥ 11.143) = 0.025 and P(χ2 ≥ 0.484) = 0.975⇒ P(0.484 ≤ 24.732/σ2 ≤ 11.143) = 0.95⇒ P(24.732/11.143 ≤ σ2 ≤ 24.732/0.484) = 0.95
95% CI for σ2: [24.732/11.143, 24.732/0.484] = [0.220, 51.0999]95% CI for σ: [1.490, 7.148]Important!: These calculations use the fact that Xis are normally distributed. Ifit is not the case, we cannot use χ2-distributions!
![Page 129: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/129.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Examples
Example 7 (b)
Let X1, X2, . . . , Xn ∼ N (µ, σ) IDD with µ = 5 and unknown σ. The realizationsfor X1, . . . , X5 are 3.5, 5.7, 1.2, 6.8, and 7.1. What values of σ are reasonableLet χ2 def
= (n−1)s2
σ2 ∼ χ2n−1 = χ2
4
X = 15 (3.5 + 5.7 + 1.2 + 6.8 + 7.1) = 4.86
(n − 1)s2 =∑n
i=1(xi − x)2 = 24.732⇒ χ2 = 24.732
σ2
Construct a 95% confidence interval for σ :
Table A5: P(χ2 ≥ 11.143) = 0.025 and P(χ2 ≥ 0.484) = 0.975⇒ P(0.484 ≤ 24.732/σ2 ≤ 11.143) = 0.95⇒ P(24.732/11.143 ≤ σ2 ≤ 24.732/0.484) = 0.95
95% CI for σ2: [24.732/11.143, 24.732/0.484] = [0.220, 51.0999]95% CI for σ: [1.490, 7.148]Important!: These calculations use the fact that Xis are normally distributed. Ifit is not the case, we cannot use χ2-distributions!
![Page 130: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/130.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Examples
Example 7 (b)
Let X1, X2, . . . , Xn ∼ N (µ, σ) IDD with µ = 5 and unknown σ. The realizationsfor X1, . . . , X5 are 3.5, 5.7, 1.2, 6.8, and 7.1. What values of σ are reasonableLet χ2 def
= (n−1)s2
σ2 ∼ χ2n−1 = χ2
4
X = 15 (3.5 + 5.7 + 1.2 + 6.8 + 7.1) = 4.86
(n − 1)s2 =∑n
i=1(xi − x)2 = 24.732
⇒ χ2 = 24.732σ2
Construct a 95% confidence interval for σ :
Table A5: P(χ2 ≥ 11.143) = 0.025 and P(χ2 ≥ 0.484) = 0.975⇒ P(0.484 ≤ 24.732/σ2 ≤ 11.143) = 0.95⇒ P(24.732/11.143 ≤ σ2 ≤ 24.732/0.484) = 0.95
95% CI for σ2: [24.732/11.143, 24.732/0.484] = [0.220, 51.0999]95% CI for σ: [1.490, 7.148]Important!: These calculations use the fact that Xis are normally distributed. Ifit is not the case, we cannot use χ2-distributions!
![Page 131: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/131.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Examples
Example 7 (b)
Let X1, X2, . . . , Xn ∼ N (µ, σ) IDD with µ = 5 and unknown σ. The realizationsfor X1, . . . , X5 are 3.5, 5.7, 1.2, 6.8, and 7.1. What values of σ are reasonableLet χ2 def
= (n−1)s2
σ2 ∼ χ2n−1 = χ2
4
X = 15 (3.5 + 5.7 + 1.2 + 6.8 + 7.1) = 4.86
(n − 1)s2 =∑n
i=1(xi − x)2 = 24.732⇒ χ2 = 24.732
σ2
Construct a 95% confidence interval for σ :
Table A5: P(χ2 ≥ 11.143) = 0.025 and P(χ2 ≥ 0.484) = 0.975⇒ P(0.484 ≤ 24.732/σ2 ≤ 11.143) = 0.95⇒ P(24.732/11.143 ≤ σ2 ≤ 24.732/0.484) = 0.95
95% CI for σ2: [24.732/11.143, 24.732/0.484] = [0.220, 51.0999]95% CI for σ: [1.490, 7.148]Important!: These calculations use the fact that Xis are normally distributed. Ifit is not the case, we cannot use χ2-distributions!
![Page 132: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/132.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Examples
Example 7 (b)
Let X1, X2, . . . , Xn ∼ N (µ, σ) IDD with µ = 5 and unknown σ. The realizationsfor X1, . . . , X5 are 3.5, 5.7, 1.2, 6.8, and 7.1. What values of σ are reasonableLet χ2 def
= (n−1)s2
σ2 ∼ χ2n−1 = χ2
4
X = 15 (3.5 + 5.7 + 1.2 + 6.8 + 7.1) = 4.86
(n − 1)s2 =∑n
i=1(xi − x)2 = 24.732⇒ χ2 = 24.732
σ2
Construct a 95% confidence interval for σ :
Table A5: P(χ2 ≥ 11.143) = 0.025 and P(χ2 ≥ 0.484) = 0.975⇒ P(0.484 ≤ 24.732/σ2 ≤ 11.143) = 0.95⇒ P(24.732/11.143 ≤ σ2 ≤ 24.732/0.484) = 0.95
95% CI for σ2: [24.732/11.143, 24.732/0.484] = [0.220, 51.0999]95% CI for σ: [1.490, 7.148]Important!: These calculations use the fact that Xis are normally distributed. Ifit is not the case, we cannot use χ2-distributions!
![Page 133: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/133.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Examples
Example 7 (b)
Let X1, X2, . . . , Xn ∼ N (µ, σ) IDD with µ = 5 and unknown σ. The realizationsfor X1, . . . , X5 are 3.5, 5.7, 1.2, 6.8, and 7.1. What values of σ are reasonableLet χ2 def
= (n−1)s2
σ2 ∼ χ2n−1 = χ2
4
X = 15 (3.5 + 5.7 + 1.2 + 6.8 + 7.1) = 4.86
(n − 1)s2 =∑n
i=1(xi − x)2 = 24.732⇒ χ2 = 24.732
σ2
Construct a 95% confidence interval for σ :
Table A5: P(χ2 ≥ 11.143) = 0.025 and P(χ2 ≥ 0.484) = 0.975
⇒ P(0.484 ≤ 24.732/σ2 ≤ 11.143) = 0.95⇒ P(24.732/11.143 ≤ σ2 ≤ 24.732/0.484) = 0.95
95% CI for σ2: [24.732/11.143, 24.732/0.484] = [0.220, 51.0999]95% CI for σ: [1.490, 7.148]Important!: These calculations use the fact that Xis are normally distributed. Ifit is not the case, we cannot use χ2-distributions!
![Page 134: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/134.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Examples
Example 7 (b)
Let X1, X2, . . . , Xn ∼ N (µ, σ) IDD with µ = 5 and unknown σ. The realizationsfor X1, . . . , X5 are 3.5, 5.7, 1.2, 6.8, and 7.1. What values of σ are reasonableLet χ2 def
= (n−1)s2
σ2 ∼ χ2n−1 = χ2
4
X = 15 (3.5 + 5.7 + 1.2 + 6.8 + 7.1) = 4.86
(n − 1)s2 =∑n
i=1(xi − x)2 = 24.732⇒ χ2 = 24.732
σ2
Construct a 95% confidence interval for σ :
Table A5: P(χ2 ≥ 11.143) = 0.025 and P(χ2 ≥ 0.484) = 0.975⇒ P(0.484 ≤ 24.732/σ2 ≤ 11.143) = 0.95
⇒ P(24.732/11.143 ≤ σ2 ≤ 24.732/0.484) = 0.95
95% CI for σ2: [24.732/11.143, 24.732/0.484] = [0.220, 51.0999]95% CI for σ: [1.490, 7.148]Important!: These calculations use the fact that Xis are normally distributed. Ifit is not the case, we cannot use χ2-distributions!
![Page 135: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/135.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Examples
Example 7 (b)
Let X1, X2, . . . , Xn ∼ N (µ, σ) IDD with µ = 5 and unknown σ. The realizationsfor X1, . . . , X5 are 3.5, 5.7, 1.2, 6.8, and 7.1. What values of σ are reasonableLet χ2 def
= (n−1)s2
σ2 ∼ χ2n−1 = χ2
4
X = 15 (3.5 + 5.7 + 1.2 + 6.8 + 7.1) = 4.86
(n − 1)s2 =∑n
i=1(xi − x)2 = 24.732⇒ χ2 = 24.732
σ2
Construct a 95% confidence interval for σ :
Table A5: P(χ2 ≥ 11.143) = 0.025 and P(χ2 ≥ 0.484) = 0.975⇒ P(0.484 ≤ 24.732/σ2 ≤ 11.143) = 0.95⇒ P(24.732/11.143 ≤ σ2 ≤ 24.732/0.484) = 0.95
95% CI for σ2: [24.732/11.143, 24.732/0.484] = [0.220, 51.0999]95% CI for σ: [1.490, 7.148]Important!: These calculations use the fact that Xis are normally distributed. Ifit is not the case, we cannot use χ2-distributions!
![Page 136: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/136.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Examples
Example 7 (b)
Let X1, X2, . . . , Xn ∼ N (µ, σ) IDD with µ = 5 and unknown σ. The realizationsfor X1, . . . , X5 are 3.5, 5.7, 1.2, 6.8, and 7.1. What values of σ are reasonableLet χ2 def
= (n−1)s2
σ2 ∼ χ2n−1 = χ2
4
X = 15 (3.5 + 5.7 + 1.2 + 6.8 + 7.1) = 4.86
(n − 1)s2 =∑n
i=1(xi − x)2 = 24.732⇒ χ2 = 24.732
σ2
Construct a 95% confidence interval for σ :
Table A5: P(χ2 ≥ 11.143) = 0.025 and P(χ2 ≥ 0.484) = 0.975⇒ P(0.484 ≤ 24.732/σ2 ≤ 11.143) = 0.95⇒ P(24.732/11.143 ≤ σ2 ≤ 24.732/0.484) = 0.95
95% CI for σ2: [24.732/11.143, 24.732/0.484] = [0.220, 51.0999]
95% CI for σ: [1.490, 7.148]Important!: These calculations use the fact that Xis are normally distributed. Ifit is not the case, we cannot use χ2-distributions!
![Page 137: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/137.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Examples
Example 7 (b)
Let X1, X2, . . . , Xn ∼ N (µ, σ) IDD with µ = 5 and unknown σ. The realizationsfor X1, . . . , X5 are 3.5, 5.7, 1.2, 6.8, and 7.1. What values of σ are reasonableLet χ2 def
= (n−1)s2
σ2 ∼ χ2n−1 = χ2
4
X = 15 (3.5 + 5.7 + 1.2 + 6.8 + 7.1) = 4.86
(n − 1)s2 =∑n
i=1(xi − x)2 = 24.732⇒ χ2 = 24.732
σ2
Construct a 95% confidence interval for σ :
Table A5: P(χ2 ≥ 11.143) = 0.025 and P(χ2 ≥ 0.484) = 0.975⇒ P(0.484 ≤ 24.732/σ2 ≤ 11.143) = 0.95⇒ P(24.732/11.143 ≤ σ2 ≤ 24.732/0.484) = 0.95
95% CI for σ2: [24.732/11.143, 24.732/0.484] = [0.220, 51.0999]95% CI for σ: [1.490, 7.148]
Important!: These calculations use the fact that Xis are normally distributed. Ifit is not the case, we cannot use χ2-distributions!
![Page 138: Lecture 13: Some Important Continuous Probability ... · PDF filebeamer-tu-logo Erlang distributionVarious Exercises Chi-squared distribution Lecture 13: Some Important Continuous](https://reader031.fdocuments.us/reader031/viewer/2022021816/5a7056967f8b9aac538bd2e1/html5/thumbnails/138.jpg)
beamer-tu-logo
Erlang distribution Various Exercises Chi-squared distribution
Examples
Example 7 (b)
Let X1, X2, . . . , Xn ∼ N (µ, σ) IDD with µ = 5 and unknown σ. The realizationsfor X1, . . . , X5 are 3.5, 5.7, 1.2, 6.8, and 7.1. What values of σ are reasonableLet χ2 def
= (n−1)s2
σ2 ∼ χ2n−1 = χ2
4
X = 15 (3.5 + 5.7 + 1.2 + 6.8 + 7.1) = 4.86
(n − 1)s2 =∑n
i=1(xi − x)2 = 24.732⇒ χ2 = 24.732
σ2
Construct a 95% confidence interval for σ :
Table A5: P(χ2 ≥ 11.143) = 0.025 and P(χ2 ≥ 0.484) = 0.975⇒ P(0.484 ≤ 24.732/σ2 ≤ 11.143) = 0.95⇒ P(24.732/11.143 ≤ σ2 ≤ 24.732/0.484) = 0.95
95% CI for σ2: [24.732/11.143, 24.732/0.484] = [0.220, 51.0999]95% CI for σ: [1.490, 7.148]Important!: These calculations use the fact that Xis are normally distributed. Ifit is not the case, we cannot use χ2-distributions!