ANOVA - Pennsylvania State University
Transcript of ANOVA - Pennsylvania State University
![Page 1: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/1.jpg)
ANOVA
![Page 2: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/2.jpg)
An Old Research Question
The impact of TV on high-school grade
Watch or not watch
Two groups
The impact of TV hours on high-school grade
Exactly how much TV watching would make
difference
Multiple groups
Not watch, watch a little, watch regularly
![Page 3: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/3.jpg)
Then we could have
something like this
![Page 4: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/4.jpg)
What Should We Do?
![Page 5: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/5.jpg)
Should t-Test Be Used?
Multiple comparison
Increasing the chance of
Type I error
0
0.2
0.4
0.6
0.8
1
0 10 20 30 40 50
![Page 6: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/6.jpg)
Multiple Comparison Is
Common
In particular in factorial design
Single factor
Multiple levels: previous example
Multiple factors
Impact of TV watching and library visit
![Page 7: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/7.jpg)
Terminology
Factor
The independent variable that designates the
groups being compared
TV watching and library visit
Levels
Individual conditions or values that make up
a factor
Factorial design
A study that combines two or more factors
![Page 8: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/8.jpg)
The research study uses two factors
One factor uses two levels of therapy technique (I
versus II)
The second factor uses three levels of time
(before, after, and 6 months after).
Figure 12.2
Two-Factor Research Design
![Page 9: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/9.jpg)
Figure 12.2
Two-Factor Research Design
![Page 10: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/10.jpg)
Also notice that the therapy factor uses two
separate groups (independent measures)
and the time factor uses the same group for
all three levels (repeated measures).
We have 15 comparisons!
Figure 12.2
Two-Factor Research Design
0
0.2
0.4
0.6
0.8
1
0 10 20 30 40 50
![Page 11: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/11.jpg)
How to deal with this
problem?
![Page 12: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/12.jpg)
Analysis of Variance
Analysis of variance
Also called ANOVA
Used to evaluate mean differences between
two or more treatments (advantage over t-
test)
Uses sample data as basis for drawing
general conclusions about populations
![Page 13: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/13.jpg)
Analysis of Variance
Null hypothesis: the level or value on the
factor does not affect the dependent variable
In the population, this is equivalent to saying that
the means of the groups do not differ from each
other
Alternative hypothesis: There is at least one
mean difference among the populations
All means are different from every other mean
Some means are not different from some others,
but other means do differ from some means
3210 : H
![Page 14: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/14.jpg)
ANOVA: Statistics
F test
F-ratio: based on variance instead of sample mean
difference
Numerator: Variance caused by differences among sample
means
Denominator: Variance be expected if there is no treatment
effect
chancebyexpecteddifference
meanssamplebetweendifferenceobtainedt
chance)by (error effect treatmentnowith expectede)(differencvariance
meanssamplebetweene)(differencvarianceF
![Page 15: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/15.jpg)
Logic of ANOVA
A study with three
treatments
![Page 16: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/16.jpg)
Sources of Variability
Between Treatments
Systematic differences caused
by treatments
Random, unsystematic differences
Individual differences
Experimental (measurement) error
![Page 17: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/17.jpg)
What if the null
hypothesis is true?
![Page 18: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/18.jpg)
F-Ratio
The ratio of the variance between treatments
to the variance within treatments
(treatment effects + chance) / (chance)
If no treatment effect, F should be 1
Otherwise, F should be larger than 1.
![Page 19: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/19.jpg)
Experimental Design
Simple experiments
Single factor
Between-subjects design
Within-subjects design
Factorial experiments
More factors
2 x 2
These design all involve multiple treatments
ANOVA would be needed.
![Page 20: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/20.jpg)
![Page 21: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/21.jpg)
Numerator of F-ratio
Numerator of F-ratio
Denominator of F-ratio
Denominator of F-ratio
![Page 22: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/22.jpg)
Logic of Repeated-Measures
ANOVA
Comparing variance
Between-treatments vs. within-treatments
Removing the difference between subjects
s)difference individual (chancebyexpectedvariance
s)difference individual ( treatmentsbetweenvarianceF
without
without
chancebyexpectedvariance
treatmentsbetweenvarianceF
![Page 23: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/23.jpg)
ANOVA
Notation and Formulas
![Page 24: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/24.jpg)
k: the number of treatment
n: the number of scores in each treatment
N: the number of total scores in the study
SX or T: the sum of the scores for each
treatment
G: the sum of all the scores in the study
G = S(SX) = ST
SX2, SS, s2, df,
![Page 25: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/25.jpg)
Figure 12.4 ANOVA
Calculation Structure and
Sequence
![Page 26: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/26.jpg)
Figure 12.5 Partitioning SS
for Independent-measures
ANOVA
![Page 27: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/27.jpg)
ANOVA equations
N
GXSStotal
22
treatment each insidetreatmentswithin SSSS
N
G
n
TSS treatmentsbetween
22
![Page 28: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/28.jpg)
Degrees of Freedom Analysis
Total degrees of freedom
dftotal= N – 1
Within-treatments degrees of freedom
dfwithin= N – k
Between-treatments degrees of freedom
dfbetween= k – 1
![Page 29: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/29.jpg)
Figure 12.6 Partitioning
Degrees of Freedom
![Page 30: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/30.jpg)
Mean Squares and F-ratio
within
withinwithinwithin
df
SSsMS 2
between
betweenbetweenbetween
df
SSsMS 2
within
between
within
between
MS
MS
s
sF
2
2
![Page 31: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/31.jpg)
ANOVA Summary Table
Source SS df MS F
Between Treatments 40 2 20 10
Within Treatments 20 10 2
Total 60 12
• Concise method for presenting ANOVA results
• Helps organize and direct the analysis process
• Convenient for checking computations
• “Standard” statistical analysis program output
![Page 32: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/32.jpg)
Distribution of F-ratios
If the null hypothesis is true, the value of F
will be around 1.00
Because F-ratios are computed from two
variances, they are always positive numbers
Table of F values is organized by two df
df numerator (between) shown in table columns
df denominator (within) shown in table rows
![Page 33: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/33.jpg)
Figure 12.7
Distribution of F-ratios
![Page 34: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/34.jpg)
ANOVA Test
Uses the same four steps that have been
used in earlier hypothesis tests.
Computation of the test statistic F is done
in stages
Compute SStotal, SSbetween, SSwithin
Compute MStotal, MSbetween, MSwithin
Compute F
![Page 35: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/35.jpg)
Measuring Effect size for
ANOVA
Compute percentage of variance accounted
for by the treatment conditions
In published reports of ANOVA, effect size is
usually called η2 (“eta squared”)
r2 concept (proportion of variance explained)
total
treatments between
SS
SS2
![Page 36: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/36.jpg)
In the Literature
Treatment means and standard deviations
are presented in text, table or graph
Results of ANOVA are summarized, including
F and df
p-value
η2
• E.g., F(3,20) = 6.45, p<.01, η2 = 0.492
![Page 37: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/37.jpg)
Example
For each
experiment
N = 14
![Page 38: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/38.jpg)
Experiment A
Source SS df MS F
Between Treatments
Within Treatments
Total
![Page 39: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/39.jpg)
Experiment B
Source SS df MS F
Between Treatments
Within Treatments
Total
![Page 40: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/40.jpg)
![Page 41: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/41.jpg)
post hoc Tests
ANOVA compares all individual mean
differences simultaneously, in one test
A significant F-ratio indicates that at least one
difference in means is statistically significant
Does not indicate which means differ significantly
from each other!
post hoc tests are follow up tests done to
determine exactly which mean differences
are significant, and which are not
![Page 42: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/42.jpg)
Tukey’s Honestly Significant
Difference
A single value that determines the minimum
difference between treatment means that is
necessary to claim statistical significance–a
difference large enough that p < αexperimentwise
Honestly Significant Difference (HSD)
n
MSqHSD within
![Page 43: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/43.jpg)
![Page 44: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/44.jpg)
![Page 45: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/45.jpg)
A vs. B: MA – MB = 2.44 > HSD significant
B vs. C: MB – MC = 1.66 < HSD
A vs. C: MA – MC = 4.00 > HSD significant
![Page 46: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/46.jpg)
The Scheffé Test
The Scheffé test is one of the safest of all
possible post hoc tests
Uses an F-ratio to evaluate significance of the
difference between two treatment conditions
groups twoof SS with calculatedB A versus
within
between
MS
MSF
![Page 47: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/47.jpg)
Between A & B
![Page 48: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/48.jpg)
A & B F(2,24) = 3.36
B & C F(2,24) = 1.36
A & C F(2,24) = 9.00
df = 2, 24 and α = .05
the critical value for F: 3.40
Only the difference between A&C is significant.
![Page 49: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/49.jpg)
Relationship between ANOVA
and t tests
For two independent samples, either t or F
can be used
Always result in same decision
F = t2
For any value of α, (tcritical)2 = Fcritical
![Page 50: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/50.jpg)
Figure 12.10
Distribution of t and F statistics
![Page 51: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/51.jpg)
Independent Measures ANOVA
Assumptions
The observations within each sample must
be independent
The population from which the samples are
selected must be normal
The populations from which the samples are
selected must have equal variances
(homogeneity of variance)
Violating the assumption of homogeneity of
variance risks invalid test results
![Page 52: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/52.jpg)
To Report ANOVA Result
The subjects averaged MA = 3, MB = 5.44, and MC = 7 in three treatments respectively. ANOVA indicated a significant difference, F(2, 24) = 9.15, p<.05, 2 = ….
Post hoc analysis (Tukey’s HSD) indicated significant difference between Treatments A and B, as well as between Treatments A and C (HSD = 2.36).
or
Post hoc analysis (Sheffé) indicated significant difference between Treatments A and C only, FA vs. C (2,24) = 9, p<.05.
![Page 53: ANOVA - Pennsylvania State University](https://reader031.fdocuments.us/reader031/viewer/2022013022/61d17e6b0a4cc6640551419a/html5/thumbnails/53.jpg)
Homework
12.22