Scribd
Upload
74 views2 pages

Skewed Student-t Distribution Analysis

The document discusses comparing different distributions in the fGarch package in R, including the skew-Student-t and Student-t distributions. It then demonstrates using the garchOxFit and garchFit functions to estimate GARCH models with normal, Student-t, and skewed Student-t innovations on log-transformed monthly Intel stock return data from 1973 to the present. Various diagnostics are performed on the residuals.

Uploaded by

datsno
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
74 views2 pages

Skewed Student-t Distribution Analysis

The document discusses comparing different distributions in the fGarch package in R, including the skew-Student-t and Student-t distributions. It then demonstrates using the garchOxFit and garchFit functions to estimate GARCH models with normal, Student-t, and skewed Student-t innovations on log-transformed monthly Intel stock return data from 1973 to the present. Various diagnostics are performed on the residuals.

Uploaded by

datsno
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

6/18/12 6:17 PM

> setwd("C:/Users/rst/teaching/bs41202/sp2010")
### Compare skew-Student-t and Student-t distributions
### in fGarch packet, the commands are sstd and std, respectively.
> x1=rstd(5000,0,1,5) #(nobs, mean, sd, nu
> x2=rsstd(5000,0,1,5,0.8) # skew to the left (nobs, mean,sd,nu,xi) where xi is the skew
parameter.
> x3=rsstd(5000,0,1,5,1.5) # skew to the right
> par(mfcol=c(1,2))
> hist(x1,nclass=50)
> hist(x2,nclass=50)
> hist(x1,nclass=50)
> hist(x3,nclass=50)

### Below are commands for Ox-G@RCH estimation ###


> da=read.table("m-intc7303.txt",header=T)
> intc=log(da[,2]+1)

> source("garchoxfit_R.txt") %Need to download the file garchoxfit_R.txt

> x=ts(intc,frequency=12,start=c(1973,1))
> plot(x)
> acf(intc)
> acf(intc^2)
> Box.test(intc^2,lag=10,type='Ljung')
> pacf(intc^2,lag=10)
> m1=garchOxFit(formula.mean=~arma(0,0),formula.var=~garch(0,3),series=intc)
> m1=garchOxFit(formula.mean=~arma(0,0),formula.var=~garch(0,1),series=intc)
> names(m1)
> par(mfcol=c(2,1))
> plot(intc,type='l')
> plot(sqrt(m1$condvars),type='l')
> par(mfcol=c(1,1))

> sresi=m1$residuals/sqrt(m1$condvars) % Compute standardized residuals


> qqnorm(sresi) % Obtain normal prob. plot
> qqline(sresi)

> Box.test(sresi,10,type='Ljung')
> Box.test(sresi^2,10,type='Ljung')
% Use Student-t innovations
> m1=garchOxFit(formula.mean=~arma(0,0),formula.var=~garch(0,1),series=intc,cond.dist="t")
> sresi=m1$residuals/sqrt(m1$condvars) % Compute standardized residuals
> qqplot(rt(10000,6.0),sresi) % t-prob plot.
> qqline(sresi)

> #### Use fGarch package of RMetrics in R ####


> library(fGarch)
> m2=garchFit(~garch(3,0),data=intc) % lots of output
> m2=garchFit(~garch(3,0),data=intc,trace=F) %no output printed.
> summary(m2) % Obtain results and model checking statististics
> sresi=residuals(m2,standardize=T) % Obtain standardized residuals - epsilon(t)-hat
> sigma.t=volatility(m2) % obtain the fitted volatility sigma_t.

> qqnorm(sresi)
> qqline(sresi)

http://faculty.chicagobooth.edu/ruey.tsay/teaching/bs41202/sp2010/Rcommands_lec4.txt Page 1 of 2
6/18/12 6:17 PM

> m2=garchFit(~garch(1,0),data=intc,trace=F)
> summary(m2)

> predict(m2,6) % prediction

# use Student-t innovations

> m2=garchFit(~garch(1,0),data=intc,trace=F,cond.dist=c("std"))
> summary(m2)

# use skewed Student-t innovations


> m3=garchFit(~garch(1,0),data=intc,trace=F,cond.dist=c("sstd"))
> summary(m3)

# Use ARMA(p,q)+GARCH(1,1) model with normal innovations


> m4=garchFit(~arma(p,q)+garch(1,0),data=intc,trace=F)
> summary(m4)

http://faculty.chicagobooth.edu/ruey.tsay/teaching/bs41202/sp2010/Rcommands_lec4.txt Page 2 of 2

You might also like