40052 - predictable manner? iii. A plot of the residuals...

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

View Full Document Right Arrow Icon
STATISTICS 4005 ASSIGNMENT 2 Due date: February 12, 2004 1. Consider the model Z t = α 0 + α 1 t 2 + α 2 t 4 + a t , t = 1 , . . . , 5 where a t ’s are independently, identically distributed as N (0 , σ 2 a ). Write the model in matrix form. 2. Let { Y t } be a stationary process with V ar ( Y t ) = 1 and autocorrelation function ρ k = 0 . 5 k for k = 0 , 1 , 2 , ... . Find V ar ± 1 3 3 X t =1 Y t ² . 3. Let X 1 , X 2 , ..., X 200 denote 200 consecutive observations of a stationary time series with mean μ and autocovariances γ k ’s. Let ¯ X = 200 X i =1 X i / 200. (a) 4 marks Show that ¯ X is an unbiased estimator of μ . (b) 4 marks Calculate V ar ( ¯ X ) in terms of γ k ’s. 4. Fit the data set “dataset1.xls” by the following two models: (a) A model Z t = μ t + X t where E ( X t ) = 0, μ t = β 0 + β 1 cos( 2 πt 12 ) + β 2 sin( 2 πt 12 ) + β 3 cos( 2 πt 6 ) + β 4 sin( 2 πt 6 ) (b) A seasonal mean model (one mean for each month) - remember to omit the constant term from the fit. With each fit, include a residual analysis, i.e. i. A multiple time series plot of the data and fitted values. ii. A time series plot of the residuals. Does the residuals oscillate in a
Background image of page 1

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

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

Unformatted text preview: predictable manner? iii. A plot of the residuals against the fitted values. Does the plot show non-constancy of error variance? iv. A histogram of residuals (with Options: Lower Bound = -10, Upper Bound = 14 and Interval Width = 2 in Splus) v. A plot of the residuals against the quantiles of Standard Normal. Ac-cording to (iii) and (iv), does the residuals look like normal? vi. An autocorrelation plot of the residuals, with Maximum Lag 36. (c) For each model, calculate by hand the fitted value and the actual residual for t = 18. (d) Which would you prefer, in practice? Justify your choice? NOTE: The data set “dataset1.xls” can be downloaded from http://www.sta.cuhk.edu.hk/khwu/courses/sta4005/ under the subsection Time Series Data used for Assignments....
View Full Document

This note was uploaded on 01/20/2012 for the course STA 4005 taught by Professor ? during the Spring '08 term at CUHK.

Page1 / 2

40052 - predictable manner? iii. A plot of the residuals...

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