Assignment_3_S07_Solution

Assignment_3_S07_Solution - 1. The original form can be...

Info iconThis preview shows pages 1–6. Sign up to view the full content.

View Full Document Right Arrow Icon
1. The original form can be written as: Zt - a*Zt-2 = et + b*et-2 (1-a*B^2)Zt = (1+ b*B^2) et-2 If Zt is weakly stationary, all the roots of (1-a*B^2) = 0 should be outside the unit circle, assume a is not 0, B= a 1 or - a 1 if a> 0 and a 1 i or - a 1 i if a<0 So a 1 > 1 and i a 1 >1, which gives ) 1 , 0 ( ) 0 , 1 ( a Since Zt=a*Zt-2 +et + b*et-2 Zt+2=a*Zt + et+2 + b*et = a*Zt + b*et 2-step-ahead predictor: t t t e b Z a Z ˆ ˆ ˆ * * 2 + = + where and are estimated coefficients of a and b. * a * b 2. a) > mydata<-data$stock[1:370] > data<-read.table("C:/companyGdata.txt",header=T) > acf(mydata)
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
0 5 10 15 20 25 0.0 0.4 0.8 Lag ACF Series mydata Comment: This acf plot shows long range dependence, which decays hyperbolically. All lags are significant up to lag 25. > pacf(mydata) 5 1 01 52 02 5 -0.2 0.2 0.6 1.0 Lag Partial ACF mydata
Background image of page 2
Comment: The data are correlated. Few lags are significant up to lag 13. b) > lgdata=log(mydata) > ts.plot(diff(lgdata)) (take log transformation and difference once) Time diff(lgdata) 0 100 200 300 -0.2 0.0 0.1 0.2 0.3 > acf(diff(lgdata) )
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
0 5 10 15 20 25 0.0 0.4 0.8 Lag ACF Series diff(lgdata) Comment: All the lags are inside the border, the data is not correlated. > pacf(diff(lgdata)) 5 1 01 52 02 5 -0.10 0.00 0.05 0.10 Lag Partial ACF Series diff(lgdata)
Background image of page 4
Comment: All the lags are inside the border except lag 23, which is simply a sample error. The data is not correlated. c) > ar.yw(diff(lgdata),order.max=10) Call: ar.yw.default(x = diff(lgdata), order.max = 10) Coefficients: 1 -0.0899 Order selected 1 sigma^2 estimated as 0.003201
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 6
This is the end of the preview. Sign up to access the rest of the document.

Page1 / 14

Assignment_3_S07_Solution - 1. The original form can be...

This preview shows document pages 1 - 6. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online