{[ promptMessage ]}

Bookmark it

{[ promptMessage ]}

Assignment_3_S07

# Assignment_3_S07 - Homework 3 STAT 443 Spring 2007 1...

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

Homework 3 STAT 443 Spring 2007 1. Consider an ARMA(2,2) model with e t ~ WN(0,1) Z t = a Z t-2 + e t + be t-2. What assumptions do we need to ensure that Z_t is a weakly stationary process? Derive a formula for 2-steps ahead predictor of Z t. 2. DESCRIPTIVE ABSTRACT: Stock prices of the company G in US dollars over the period from July 9, 1998 through December 31, 1999. (Only business days are shown.) YOUR TASK: To forecast stock prices for the company G for December 27, 28, 29, 30 and 31 of 1999. So the training set is from July 9, 1998 through December 23, 1999. You should a) provide an acf and pacf plots of the stock data and interpret these plots; b) difference the data and/or apply variance stabilizing transformations if needed; repeat (a); c) suggest an AR, MA or ARMA model for the stock prices (possibly preprocessed) and estimate the chosen model; d) justify your model by comparing with other models (for example, using AIC); e) provide diagnostics of the assumptions (white noise + normality), i.e. verify that residuals are homoscedastic (residual plots),

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

View Full Document
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

### Page1 / 9

Assignment_3_S07 - Homework 3 STAT 443 Spring 2007 1...

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

View Full Document
Ask a homework question - tutors are online