HW08b_sol - Homework 12 Solutions Problem 1 Part A...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
Homework 12 Solutions Page 1 of 5 Problem 1 Part A ARIMA(1,1,0) = t t t Y Y 1 1 0 The model does not appear to be adequate as there is a significant autocorrelation at lag 2 with t = –3.65. At that point the LBQ is also greater than the related 2 05 . 0 value thus also indicating that the errors are not a random series. Part B The model might be modified by incorporating a second difference component to the model. Both the Akaike information criterion and Bayesian information criterion can be used to evaluate the effectiveness of the new model. Problem 2 Part A From table P-7B the autocorrelations of the original data continue to be significant for some time this suggesting a non-stationary time series. Original Data 0.00 0.20 0.40 0.60 0.80 1.00 123456789 1 0 1 1 1 2 Lag AutoCorr The autocorrelations for the first-differenced series (table P-7C) suggest that a time series of first-difference is stationary and that this is optimal over the second-differenced series (–0.40 is closer to zero than –0.53).
Background image of page 1

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

View Full DocumentRight Arrow Icon
Image of page 2
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 06/18/2011 for the course IEOR 4307 taught by Professor Dr.kosrowdehnad during the Summer '10 term at Columbia.

Page1 / 5

HW08b_sol - Homework 12 Solutions Problem 1 Part A...

This preview shows document pages 1 - 2. Sign up to view the full document.

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