This preview has intentionally blurred sections. Sign up to view the full version.View Full Document
Unformatted text preview: STAT 420 Fall 2008 Homework #13 (10 points) (due Wednesday, December 10, by 3:00 p.m.) 1. We will use the R time series functions to simulate, plot, and calculate sample ACF and PACF. a) To generate the AR(1) model: Y t = φ 1 Y t – 1 + e t where e t are N(0, 1) random variables, we will use the function arima.sim . You can use the help function to see more about this function. To generate 100 observations from an AR(1) process with φ 1 = 0.5, use the commands below. The set.seed function will produce the same sequence of N(0,1) random variables, so that everyone in the class generates the same sequence! set.seed(1) #set seed for generating random sequence y0.5 = arima.sim(n=100, model=list(ar=0.5)) #simulate AR(1) par(mfrow=c(3,1)) #3 plots per page ts.plot(y0.5) #plot series acf(y0.5) #plot sample ACF pacf(y0.5) #plot sample PACF Describe the patterns you observe in the sample ACF and PACF. They should be consistent with the theoretical ACF and PACF....
View Full Document
- Spring '10
- Randomness, sample acf