Econ 7933: Financial Time Series: Introduction

39
Econ 7933: Financial Time Series: Introduction Sheng-Kai Chang (NTU) Fall, 2015 Sheng-Kai Chang (NTU) Econ 7933: Financial Time Series Fall, 2015 1 / 39

Transcript of Econ 7933: Financial Time Series: Introduction

Page 1: Econ 7933: Financial Time Series: Introduction

Econ 7933: Financial Time Series: Introduction

Sheng-Kai Chang (NTU)

Fall, 2015

Sheng-Kai Chang (NTU) Econ 7933: Financial Time Series Fall, 2015 1 / 39

Page 2: Econ 7933: Financial Time Series: Introduction

Examples of Fnancial time series

Daily log returns of Apple stock: 2005 to 2014.

U.S. monthly unemployment rates

U.S. daily interesrate rate of 10-year Treasury Notes

The VIX index

Exchange rate between US Dollar vs Euro

Sheng-Kai Chang (NTU) Econ 7933: Financial Time Series Fall, 2015 2 / 39

Page 3: Econ 7933: Financial Time Series: Introduction

setwd("D:/R/FTS/Data")

library(quantmod)

library(downloader)

getSymbols("AAPL",from="2005-01-01",to="2014-12-31")

## [1] "AAPL"

chartSeries(AAPL, theme="white")

100

200

300

400

500

600

700

AAPL [2005−01−03/2014−12−31]

Last 110.379997

Volume (millions):41,403,400

0

200

400

600

800

...... 03 2005 ...... 02 2007 ...... 04 2010 ...... 02 2012 ......... 31 2014

Sheng-Kai Chang (NTU) Econ 7933: Financial Time Series Fall, 2015 3 / 39

Page 4: Econ 7933: Financial Time Series: Introduction

chartSeries(AAPL$AAPL.Adjusted, theme="white")

0

20

40

60

80

100

120

$AAPLAAPL.Adjusted

[2005−01−03/2014−12−31]

Last 108.99538

...... 03 2005 ...... 02 2007 ...... 04 2010 ...... 02 2012 ......... 31 2014

Sheng-Kai Chang (NTU) Econ 7933: Financial Time Series Fall, 2015 4 / 39

Page 5: Econ 7933: Financial Time Series: Introduction

AAPL.rtn=diff(log(AAPL$AAPL.Adjusted))

hist(AAPL.rtn)

Histogram of AAPL.rtn

AAPL.rtn

Fre

quen

cy

−0.20 −0.15 −0.10 −0.05 0.00 0.05 0.10 0.15

020

040

060

080

010

00

Sheng-Kai Chang (NTU) Econ 7933: Financial Time Series Fall, 2015 5 / 39

Page 6: Econ 7933: Financial Time Series: Introduction

chartSeries(AAPL.rtn, theme="white")

−0.20

−0.15

−0.10

−0.05

0.00

0.05

0.10

AAPL.rtn [2005−01−04/2014−12−31]

Last −0.0192020203673824

...... 04 2005 ...... 02 2007 ...... 04 2010 ...... 02 2012 ......... 31 2014

Sheng-Kai Chang (NTU) Econ 7933: Financial Time Series Fall, 2015 6 / 39

Page 7: Econ 7933: Financial Time Series: Introduction

getSymbols("UNRATE", src="FRED")

## [1] "UNRATE"

chartSeries(UNRATE, theme="white")

4

6

8

10

UNRATE [1948−01−01/2015−08−01]

Last 5.1

...... 1948 ...... 1960 ...... 1975 ...... 1990 ...... 2005

Sheng-Kai Chang (NTU) Econ 7933: Financial Time Series Fall, 2015 7 / 39

Page 8: Econ 7933: Financial Time Series: Introduction

U.S. Government Bonds: Treasury Bills, Treasury Notes, Treasury Bonds

Treasury bills (T-Bills) mature in one year or less. They do not payinterest prior to maturity and are sold at a discount of the face value(par value).

The commonly used maturities are 28 days (1 months), 91 days (3months), 182 days (6 months), and 364 days (1 year).

Treasury Notes (T-Notes) matures in 1-10 years. They have a couponpayment every 6 months and face value of $1, 000

The 10-year T-Notes has become the security most frequently quotedwhen discussing U.S. government bond market.

Treasury Bonds (T-Bonds) have longer maturities ranging from 20 to30 years. Thay have coupon payment every 6 months.

Sheng-Kai Chang (NTU) Econ 7933: Financial Time Series Fall, 2015 8 / 39

Page 9: Econ 7933: Financial Time Series: Introduction

Bond Yields and Prices

Current Yield= Annual interest paid in dollarsMarket price of the bond × 100%

For zero-coupon bonds, Current Yield= ( Face valuePurchase price )1/k − 1, where

k is time to maturity in years.

EX: if an investor paid $90 for a bond with face value of $100 and thebond paid a coupon rate 5% per annum, then the current yield of thebond is (0.05 ∗ 100)/90 ∗ 100% = 5.56%.

The current yield does not consider the time value of money since itdoes not consider the present value of the coupon payments theinvestor will receive in the future.

A more commonly used measurement of bond investment is the Yieldto Maturity (YTM).

Sheng-Kai Chang (NTU) Econ 7933: Financial Time Series Fall, 2015 9 / 39

Page 10: Econ 7933: Financial Time Series: Introduction

Yield to Maturity (YTM)

YTM is the yield obtained by equating the bond price to the presentvalue of all future payments.Suppose that the bond holder will receive k payments betweenpurchase and maturity. Let y and P be the YTM and price of thebond respectively. Then

P =C1

1 + y+

C2

(1 + y)2+ ...+

Ck + F

(1 + y)k

where F denotes the face value and Ci us the ith cash flow of couponpayment.Suppose that the coupon rate is α per annum, the number ofpayments is m per year, and the time to maturity is n year. Thencash flow of coupon payment is Fα/m and the number of paymentsis k = mn.

P =αF

m[

1

1 + y+

1

(1 + y)2+ ...+

1

(1 + y)k] +

F

(1 + y)k

=αF

my[1− 1

(1 + y)k] +

F

(1 + y)k

Sheng-Kai Chang (NTU) Econ 7933: Financial Time Series Fall, 2015 10 / 39

Page 11: Econ 7933: Financial Time Series: Introduction

The table below shows some results between bond price and YTMassuming that F = $100 and coupon rate is 5% per annum payablesemiannually, and time to maturity is 3 years.

Yield to Maturity (%) Semiannual Rat (% ) Bond price ($)

6 3.0 97.297 3.5 94.678 4.0 92.149 4.5 89.68

10 5.0 87.31

YTM is inversely proportional to the bond price.

In practice, we observe bond price, so that YTM can be calculated.

Sheng-Kai Chang (NTU) Econ 7933: Financial Time Series Fall, 2015 11 / 39

Page 12: Econ 7933: Financial Time Series: Introduction

getSymbols("^TNX", from="2007-01-01",to="2015-6-30")

## [1] "TNX"

chartSeries(TNX, theme="white")

2

3

4

5

TNX [2007−01−03/2015−06−30]

Last 2.335

Volume (100s):0

−1.0

−0.5

0.0

0.5

1.0

...... 03 2007 ...... 02 2009 ...... 03 2011 ...... 02 2013 ...... 02 2015

Sheng-Kai Chang (NTU) Econ 7933: Financial Time Series Fall, 2015 12 / 39

Page 13: Econ 7933: Financial Time Series: Introduction

TNX.rtn=diff(log(TNX$TNX.Adjusted))

chartSeries(TNX.rtn, theme="white")

−0.15

−0.10

−0.05

0.00

0.05

0.10

TNX.rtn [2007−01−04/2015−06−30]

Last 0.00171453106724051

...... 04 2007 ...... 02 2009 ...... 03 2011 ...... 02 2013 ...... 02 2015

Sheng-Kai Chang (NTU) Econ 7933: Financial Time Series Fall, 2015 13 / 39

Page 14: Econ 7933: Financial Time Series: Introduction

getSymbols("^VIX", from="2007-01-01",to="2015-6-30")

## [1] "VIX"

chartSeries(VIX, theme="white")

20

40

60

80

VIX [2007−01−03/2015−06−30]

Last 18.23

Volume (100,000s):0

0

5

10

15

20

...... 03 2007 ...... 02 2009 ...... 03 2011 ...... 02 2013 ...... 02 2015

Sheng-Kai Chang (NTU) Econ 7933: Financial Time Series Fall, 2015 14 / 39

Page 15: Econ 7933: Financial Time Series: Introduction

getSymbols("DEXUSEU", src="FRED")

## [1] "DEXUSEU"

chartSeries(DEXUSEU, theme="white")

0.8

1.0

1.2

1.4

1.6

DEXUSEU [1999−01−04/2015−09−11]

Last 1.1338

...... 04 1999 ...... 02 2003 ...... 02 2007 ...... 03 2011 ...... 02 2015

Sheng-Kai Chang (NTU) Econ 7933: Financial Time Series Fall, 2015 15 / 39

Page 16: Econ 7933: Financial Time Series: Introduction

Asset Returns:Let Pt be the price of an asset at time t, and assume nodividend.

One-period simple returnGross return: 1 + Rt = Pt

Pt−1

Simple return: Rt = PtPt−1− 1.

Multiperiod simple returnGross return: 1 + Rt(k) = Pt

Pt−k= Pt

Pt−1× Pt−1

Pt−2× ...× Pt−k+1

Pt−k

The k-period Simple net return: Rt(k) = PtPt−k− 1.

Time interval is important, default is one year.

Annualized (average) return:Annualized [Rt(k)] = [

∏k−1j=0 (1 + Rt−j)]1/k − 1

Annualized [Rt(k)] ≈ 1k

∑k−1j=0 Rt−j

Sheng-Kai Chang (NTU) Econ 7933: Financial Time Series Fall, 2015 16 / 39

Page 17: Econ 7933: Financial Time Series: Introduction

Continuously compounding: Let C be the initial capital, r be the interestannum, and n be the number of years.

A = C × exp[r × n]

Present value: C = A× exp[−r × n]

Continuously compounding (log) return:rt = ln(1 + Rt) = ln( Pt

Pt−1) = pt − pt−1

Multiperiod log returnrt(k) = ln(1 + Rt(k)) = ln[ Pt

Pt−1× Pt−1

Pt−2× · · · × Pt−k+1

Pt−k]

= rt + rt−1 + · · ·+ rt−k+1

Portfolio return with N assets and weights w :Rp,t =

∑Ni=1 wiRit

Sheng-Kai Chang (NTU) Econ 7933: Financial Time Series Fall, 2015 17 / 39

Page 18: Econ 7933: Financial Time Series: Introduction

Dividend (Dt): Rt = Pt+DtPt−1

− 1,rt = ln(Pt + Dt)− ln(Pt−1)

Excess return: Zt = Rt − R0t , zt = rt − r0t , where r0t denoted the logreturn of a risk-free interest rate.

rt = ln(1 + Rt), Rt = ert − 1.

If the returns are in percentage, then rt = 100× ln(1 + Rt100 ),

Rt = [exp( rt100 )− 1]× 100.

Aggregation of the returns1 + Rt(k) = (1 + Rt)(1 + Rt−1) · · · (1 + Rt−k+1)rt(k) = rt + rt−1 + · · ·+ rt−k+1

These two relations are important in practice, for example, obtainannual returns from monthly returns.

Sheng-Kai Chang (NTU) Econ 7933: Financial Time Series Fall, 2015 18 / 39

Page 19: Econ 7933: Financial Time Series: Introduction

Distributional properties of returns: What is the distribution of rit?

Moment of a random variable X with density f (x): r -th momentE (X r ) =

∫∞−∞ x r f (x)dx .

First moment: mean of X .

r -th central moment: E ((X − µX )r ) =∫∞−∞(x − µX )r f (x)dx

Second central moment: variance of X .

Skewness (symmetry): S(x) = E [ (X−µx )3

σ3x

].

Kurtosis (fat-tails) K (x) = E [ (X−µx )4

σ4x

], K (x)− 3 is excess kurtosis.

The mean and variance are related to long-term retrun and risk,respectively. Symmetry has important implications in holding short orlong financial positions and in risk management. Moreover, highkurtosis implies heavy (or long) tails in distribution.

Sheng-Kai Chang (NTU) Econ 7933: Financial Time Series Fall, 2015 19 / 39

Page 20: Econ 7933: Financial Time Series: Introduction

Estimation: Data {x1, ..., xT}.Sample mean: µx = 1

T

∑Tt=1 xt .

Sample variance: σ2x = 1

T−1

∑Tt=1(xt − µx)2.

Sample skewness: S(x) = 1(T−1)σ3

x

∑Tt=1(xt − µx)3.

Sample kurtosis: K (x) = 1(T−1)σ4

x

∑Tt=1(xt − µx)4.

Assume that xt is normally distributed, S(x) ∼ N(0, 6T ) and

K (x)− 3 ∼ N(0, 24T ).

Test for symmetry: S∗ = S(x)√6/T∼ N(0, 1) under normality. Decision

rule: Reject H0 of a symmetric distribution if |S∗| > Zα/2 or p-valueis less than α.

Test for tail thickness: K ∗ = K(x)−3√24/T

∼ N(0, 1) under normality.

Decision rule: Reject H0 of a symmetric distribution if |K ∗| > Zα/2 orp-value is less than α.

Sheng-Kai Chang (NTU) Econ 7933: Financial Time Series Fall, 2015 20 / 39

Page 21: Econ 7933: Financial Time Series: Introduction

A joint test (Jarque-Bera test): JB = (S∗)2 + (K ∗)2 ∼ χ22 under

normality. Decision rule: Reject H0 of normality if JB > χ22(α) or

p-value is less than α.

Empirical distribution of asset returns tend to be skewed to the leftwith heavy tails and has a higher peak than normal distribution.

Normal and lognormal: Y is lognormal if X = ln(Y ) is normal.

If X ∼ N(µ, σ2), then Y = exp(X ) is lognormal with

E (Y ) = exp(µ+ σ2

2 ), V (Y ) = exp(2µ+ σ2)[exp(σ2)− 1].

If Y is lognormal with mean µy and variance σ2y , then X = ln(Y ) is

normal with E (X ) = ln[µy√

1+σ2y

µ2y

], V (Y ) = ln[1 +σ2y

µ2y

].

Sheng-Kai Chang (NTU) Econ 7933: Financial Time Series Fall, 2015 21 / 39

Page 22: Econ 7933: Financial Time Series: Introduction

library(fBasics)

#da=read.table("d-ibm3dx7008.txt",header=T) # Load data with header into R

da=read.table("m-ibm6708.txt",header=T) # Load data with header into R

da[1,]

## date ibm sprtn

## 1 19670331 0.048837 0.03941

dim(da) # Check dimension of the data (row = sample size, col = variables)

## [1] 502 3

Sheng-Kai Chang (NTU) Econ 7933: Financial Time Series Fall, 2015 22 / 39

Page 23: Econ 7933: Financial Time Series: Introduction

ibm=da[,2] # Select the simple returns of IBM stock stored in Column 2.

plot(ibm,type='l') # Plot the simple returns.

0 100 200 300 400 500

−0.

2−

0.1

0.0

0.1

0.2

0.3

Index

ibm

Sheng-Kai Chang (NTU) Econ 7933: Financial Time Series Fall, 2015 23 / 39

Page 24: Econ 7933: Financial Time Series: Introduction

basicStats(ibm) # Compute the descriptive statistics of simple returns.

## ibm

## nobs 502.000000

## NAs 0.000000

## Minimum -0.261905

## Maximum 0.353799

## 1. Quartile -0.036942

## 3. Quartile 0.049636

## Mean 0.008865

## Median 0.005274

## Sum 4.450050

## SE Mean 0.003262

## LCL Mean 0.002456

## UCL Mean 0.015273

## Variance 0.005341

## Stdev 0.073085

## Skewness 0.263914

## Kurtosis 1.822178

Sheng-Kai Chang (NTU) Econ 7933: Financial Time Series Fall, 2015 24 / 39

Page 25: Econ 7933: Financial Time Series: Introduction

libm=log(ibm+1) # Compute the IBM log returns

basicStats(libm) # Compute descriptive statistics of log returns.

## libm

## nobs 502.000000

## NAs 0.000000

## Minimum -0.303683

## Maximum 0.302915

## 1. Quartile -0.037641

## 3. Quartile 0.048443

## Mean 0.006208

## Median 0.005260

## Sum 3.116457

## SE Mean 0.003237

## LCL Mean -0.000151

## UCL Mean 0.012567

## Variance 0.005259

## Stdev 0.072517

## Skewness -0.135343

## Kurtosis 1.693092

Sheng-Kai Chang (NTU) Econ 7933: Financial Time Series Fall, 2015 25 / 39

Page 26: Econ 7933: Financial Time Series: Introduction

t.test(ibm) # Perform t-test for mean being zero.

##

## One Sample t-test

##

## data: ibm

## t = 2.7176, df = 501, p-value = 0.006804

## alternative hypothesis: true mean is not equal to 0

## 95 percent confidence interval:

## 0.002455871 0.015273412

## sample estimates:

## mean of x

## 0.008864641

t.test(ibm,alternative=c("greater")) # Perform one-sided test.

##

## One Sample t-test

##

## data: ibm

## t = 2.7176, df = 501, p-value = 0.003402

## alternative hypothesis: true mean is greater than 0

## 95 percent confidence interval:

## 0.003489285 Inf

## sample estimates:

## mean of x

## 0.008864641

Sheng-Kai Chang (NTU) Econ 7933: Financial Time Series Fall, 2015 26 / 39

Page 27: Econ 7933: Financial Time Series: Introduction

hist(ibm,nclass=40) # Obtain histogram of IBM simple returns.

Histogram of ibm

ibm

Fre

quen

cy

−0.3 −0.2 −0.1 0.0 0.1 0.2 0.3

010

2030

4050

6070

Sheng-Kai Chang (NTU) Econ 7933: Financial Time Series Fall, 2015 27 / 39

Page 28: Econ 7933: Financial Time Series: Introduction

d1=density(libm) # Compute density function of ibm log returns

plot(d1$x,d1$y,type='l') # Plot the sample density of log returns

mu=mean(libm); s1 = sd(libm) # compute the sample mean and standard deviation of IBM log returns.

x=seq(-0.4,0.4,0.01) # create a sequence of real numbers from -0.4 to 0.4 with increment 0.01.

y=dnorm(x,mean=mu,sd=s1) # obtain normal density with mean mu and standard deviation s1.

lines(x,y,lty=2) # impose a dashed line on the density plot for comparison with normal density.

lines(x,y,col="red") #will plot a red curve.

−0.3 −0.2 −0.1 0.0 0.1 0.2 0.3

01

23

45

6

d1$x

d1$y

Sheng-Kai Chang (NTU) Econ 7933: Financial Time Series Fall, 2015 28 / 39

Page 29: Econ 7933: Financial Time Series: Introduction

normalTest(libm,method='jb') # Perform normality test.

##

## Title:

## Jarque - Bera Normalality Test

##

## Test Results:

## STATISTIC:

## X-squared: 62.8363

## P VALUE:

## Asymptotic p Value: 2.265e-14

##

## Description:

## Thu Sep 17 21:08:52 2015 by user: Sheng-Kai

Sheng-Kai Chang (NTU) Econ 7933: Financial Time Series Fall, 2015 29 / 39

Page 30: Econ 7933: Financial Time Series: Introduction

Dependence: Consider two random variables X and Y , correlationcoefficient: ρ = Cov(X ,Y )

std(X )std(Y ) .

Kendall’s tau: Let (X , Y ) be an random copy of (X ,Y ).ρτ = P[(X − X )(Y − Y ) > 0]− P[(X − X )(Y − Y ) < 0] =E [sign[(X − X )(Y − Y )]].

Kendall’s tau quantifies the probability of concordant over discordant.Here concordant means (X − X )(Y − Y ) > 0.

Spearman’s rho: rank correlation. Let Fx(x) and Fy (y) be thecumulative distribution of X and Y . ρS = ρ(Fx(X ),Fy (Y )).

Spearman’s rho is the correlation of probability-transformed variables.It is the correlation coefficient of the ranks of the data.

Sheng-Kai Chang (NTU) Econ 7933: Financial Time Series Fall, 2015 30 / 39

Page 31: Econ 7933: Financial Time Series: Introduction

x = rnorm(1000) # Generate 1000 N(0,1) random numbers

cor(x,x)

## [1] 1

cor(x,exp(x))

## [1] 0.7510654

cor(x,exp(x),method="kendall")

## [1] 1

cor(x,exp(x),method="spearman")

## [1] 1

ibm=da[,2]

sp=da[,3]

cor(ibm,sp)

## [1] 0.5949041

cor(ibm,sp,method="kendall")

## [1] 0.4223351

cor(ibm,sp,method="spearman")

## [1] 0.5897587

Sheng-Kai Chang (NTU) Econ 7933: Financial Time Series Fall, 2015 31 / 39

Page 32: Econ 7933: Financial Time Series: Introduction

Basic concepts of Time Series Models

Stationarity:- Strict: distributions are time-invariant.- Weak: first 2 moments (mean, variance and covariance) aretime-invariant.

Sample mean and sample variance are used to estimate the mean andvariance.

Lag-k autocovariance: let rt be log return,γk = Cov(rt , tt−k) = E [(rt − µ)(rt−k − µ)].

Autocorrelations: ρl =cov(rt ,rt−l )

var(rt). Note that ρ0 = 1 and ρk = ρ−k for

k 6= 0.

Existence of serial correlations implies that the return is predictableand indicating market inefficiency.

Sheng-Kai Chang (NTU) Econ 7933: Financial Time Series Fall, 2015 32 / 39

Page 33: Econ 7933: Financial Time Series: Introduction

Basic concepts of Time Series Models

Sample autocorrelation function (ACF): ρl =∑T−l

t=1 (rt−r)(rt+l−r)∑T−lt=1 (rt−r)2

, where

r is the sample mean and T is the sample size.

Test zero serial corellation (market efficiency)- Individual test: H0 : ρ1 = 0 v.s. H1 : ρ1 6= 0t = ρ1√

1/T=√T ρ1, which is asymptotically N(0, 1).

Decision rule: Reject H0 if |t| > Zα/2 or p-value is less than α.- Joint test (Ljung-Box statistics) :H0 : ρ1 = · · · = ρm = 0 v.s.H1 : ρi 6= 0

Q(m) = T (T + 2)∑m

l=1ρ2l

T−l , which is asymptotically χ2m.

Decision rule: Reject H0 if Q(m) > χ2m(α) or p-value is less than α.

Significant sample ACF does not necessarily imply market inefficiency.

Sheng-Kai Chang (NTU) Econ 7933: Financial Time Series Fall, 2015 33 / 39

Page 34: Econ 7933: Financial Time Series: Introduction

library(timeSeries)

par(mfcol=c(2,1)) # Put two plots on a sinlge page. c(2,1) means two rows and one column.

ts.plot(ibm)

ts.plot(sp)

Time

ibm

0 100 200 300 400 500

−0.

20.

00.

2

Time

sp

0 100 200 300 400 500

−0.

20.

00.

1

Sheng-Kai Chang (NTU) Econ 7933: Financial Time Series Fall, 2015 34 / 39

Page 35: Econ 7933: Financial Time Series: Introduction

tdx=(2+c(1:502))/12+1967 # create a calendar time index. The data start at March 1967 so that the index is from 3:505

par(mfcol=c(1,1)) # return to one plot per page

plot(tdx,ibm,type='l', xlab='year',ylab='ibm',main="Monthly IBM returns")

1970 1980 1990 2000 2010

−0.

2−

0.1

0.0

0.1

0.2

0.3

Monthly IBM returns

year

ibm

Sheng-Kai Chang (NTU) Econ 7933: Financial Time Series Fall, 2015 35 / 39

Page 36: Econ 7933: Financial Time Series: Introduction

acf(ibm,lag=20) # specify the number of ACF to compute

0 5 10 15 20

0.0

0.2

0.4

0.6

0.8

1.0

Lag

AC

F

Series ibm

Sheng-Kai Chang (NTU) Econ 7933: Financial Time Series Fall, 2015 36 / 39

Page 37: Econ 7933: Financial Time Series: Introduction

pacf(ibm,lag=20)

5 10 15 20

−0.

050.

000.

050.

10

Lag

Par

tial A

CF

Series ibm

Box.test(ibm,lag=10,type="Ljung") # Compute Ljung-Box Q(m) statistics

##

## Box-Ljung test

##

## data: ibm

## X-squared = 6.9444, df = 10, p-value = 0.7307

Sheng-Kai Chang (NTU) Econ 7933: Financial Time Series Fall, 2015 37 / 39

Page 38: Econ 7933: Financial Time Series: Introduction

Lag operator: Lrt = rt−1, L2rt = rt−2.

Available data at time t, Ft−1 ≡ {r1, r2, · · · , rt−1}.The return rt is decomposed into two parts given information Ft−1:rt = µt + at = E (rt |Ft−1) + σtεt .

µt is conditional mean of rt . It is the function of elements of Ft−1,and it is predictable part of rt .

at is shock or innovation at time t, it is unpredictable part of rt .

εt is an i .i .d . sequence with mean zero and variance 1.

σt is conditional standard deviation. (volatility)

Model for µt : mean equation; Model for σ2t : volatility equation.

Two purposes for time series models:- A model for µt .- Understanding models for σ2

t . (properties, forcasting, etc.)

Sheng-Kai Chang (NTU) Econ 7933: Financial Time Series Fall, 2015 38 / 39

Page 39: Econ 7933: Financial Time Series: Introduction

Linear time series

rt is linear if the predictable part is a linear function of Ft−1 and atsare i .i .d . distributed.

That is, rt can be written as rt = µ+∑∞

i=0 ψiat−i , where µ is aconstant, ψ0 = 1 and at is an i .i .d . sequence with mean zero andfinite variance.

at is shock or innovation at time t and ψi are the impulse responsesof rt .

Sheng-Kai Chang (NTU) Econ 7933: Financial Time Series Fall, 2015 39 / 39