hwk5 - IEOR E4709 Data Analysis for Financial Engineers...

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

View Full Document Right Arrow Icon
IEOR E4709 Data Analysis for Financial Engineers Solution 5 1. Problem 2.1 in Tsay’s book: Solution: From the model, 101 = 101 +0 2 100 . Taking conditional expectation at =100 ,wehave the 1-step forecast as 100 (1) = E ( 101 |F (100)) = E ( 101 |F (100)) + E (0 2 100 |F (100)) = 0 + 0 2 100 =0 002 The associated forecast error is 100 (1) = 101 100 (1) = 101 . Therefor, the standard deviation of the forecast error is p Var ( 100 (1)) = std ( 101 )=0 025 For 2-step ahead forecast, we have 102 = 102 2 101 ,andthen 101 (2) = E ( 102 |F (100)) = E ( 102 |F (100)) + E (0 2 101 |F (100)) = 0 The associated forecast error is 100 (2) = 102 100 (2) = 102 2 101 . Therefor, the standard deviation of the forecast error is p ( 100 (2)) = p ( 102 )+0 04 ( 101 )= 1 04 0255 To compute ACF of , use the model to obtain ( ( 2 2 ( 1 )=1 04 2 00065 . Cov (  1 Cov ( 2 1  1 2 2 Cov (0 2 1 1 2 2 = 0 000125 . Cov ( ,for 2 . Therefore, ACF of is 1 192 , for 2 . 2. Problem 2.4 in Tsay’s book Solution: (b) Figures 1 presents the ACF and PACF of Decile 2. We can see that lags 1 and 12 seem to be signi f cant in the acf plot, and lags 1 and 12 seem to be signi f cant in the partial acf plot.
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 10/17/2010 for the course IEOR 4709 taught by Professor Stevenkou during the Spring '10 term at Columbia.

Page1 / 8

hwk5 - IEOR E4709 Data Analysis for Financial Engineers...

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