This preview shows pages 1–3. Sign up to view the full content.
This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: STAT 420 Examples for 12/007/2010 Fall 2010 1. Consider the AR(2) process for which it is known that = 0, Y t = 1 Y t 1 + 2 Y t 2 + e t Based on a series of length N = 100, we observe y 99 = 2, y 100 = 3. a) Suppose r 1 = 0.50, r 2 = 0.55. Use the method of moments to estimate 1 and 2 . YuleWalker equations for an AR(2) process: 1 = 1 + 2 1 2 = 1 1 + 2 0.50 = 1 0.50 2 2 1 = 2 1 2 0.55 = 0.50 1 + 2 0.55 = 0.50 1 + 2 0.45 = 1.5 1 1 = 0.30 1 = 2 ( 0.30 ) 2 1 = 0.60 2 2 = 0.40 a ) If 1 and 2 are equal to your answers to part (a), is this process stationary? ( B ) = 1 + 0.3 B 0.4 B 2 = ( 1 0.5 B ) ( 1 + 0.8 B ) The roots of ( z ) = 0 are z 1 = 2 and z 2 = 1.25. Both are outside the unit circle. That is,  z 1  > 1,  z 2  > 1. The process is stationary. OR An AR(2) model is stationary if 1 < 2 < 1, 2 + 1 < 1, 2 1 < 1. 1 < 0.4 < 1, 0.4 0.3 < 1, 0.4 + 0.3 < 1. This process is stationary. b) Use your answers to part (a) to forecast y 101 , y 102 , and y 103 . Y N + 1 = + 1 ( Y N ) + 2 ( Y N 1 ) + e N + 1 1 + N y = ( ) 1 N y = E N ( Y N + 1 ) = + 1 ( y N ) + 2 ( y N 1 ) Y N + 2 = + 1 ( Y N + 1...
View
Full
Document
This note was uploaded on 12/17/2010 for the course STAT 420 taught by Professor Stepanov during the Spring '08 term at University of Illinois, Urbana Champaign.
 Spring '08
 Stepanov
 Statistics

Click to edit the document details