STAT 331 (W12) Assignment #3
(Due Thursday, March 8, in class)
1) Suppose you wish to perform a regression analysis (using the normal model) to investigate the effect of
three factors; temperature, moisture, and nutrient level, on yield of a particular cr

STAT 331: Applied Linear Models
Practice Problems 2: Solutions
version: 2016-11-08 21:54:42
Q1.
a.
i. If SSerr and SStot are the residual and total sum-of-squares, then
R2 = 1
SSerr
,
SStot
2
Radj
=1
SSerr /(n p)
SSerr
=1a
,
SStot /(n 1)
SStot
where a =

STAT 331: Applied Linear Models
Module II Multiple Linear Regression:
Theory
version: 2016-09-10 12:37:09
1. Some Useful Matrix Properties
A concise treatment of the multiple linear regression model relies quite a bit on matrix
algebra. An overview of som

ESE 302
Tony E. Smith
NOTES ON SIMPLE LINEAR REGRESSION
1. INTRODUCTION
The purpose of these notes is to supplement the mathematical development of linear
regression in Devore (2008). This development also draws on the treatment in Johnston (1963)
and Lar

Stat 331 - Project - Spring 2012
Due on Tuesday July 24th by 10:00am in M3 3112.
We are interested in building a regression model based on the 1997 COMPUSTAT sample data. The original data le has been modied to include two factors. You can access the data

Stat 331 - Tutorial 3
1. Consider the model y = X + ,
independent.
M V N (0, 2 I ). Show that and e are statistically
Solution: We have = Hy and e = (I H )y where H = X (X X )1 X . Since y
2 I ), then and e also follow a multivariate distribution (linea

Stat 331 - Tutorial 3
M V N (0, 2 I ). Show that and e are statistically
1. Consider the model y = X + ,
independent.
2. (Adapted from question 4.14 of Introduction to Regression Modeling by Bovas Abraham and Johannes Ledolter, 2006) The survival rate (i

Stat 331 - Tutorial 1
Suppose we would like to investigate the relationship between the maintenance cost (in thousands of dollars) of Boeing 787 aircraft and the number of ight hours. The dataset airline_slr.txt
is available on Learn and contains data for

Stat 331 - Tutorial 2
1. Consider the simple linear regression model yi = 0 + 1 xi + i , i = 1, 2, . . . , n with the
usual assumptions. Show that the ANOVA F-test is equivalent to the t-test for testing
D
H0 : 1 = 0. (Hint: Show that t2 = F .)
Solution:

Stat 331 - Tutorial 1
Suppose we would like to investigate the relationship between the maintenance cost (in thousands of dollars) of Boeing 787 aircraft and the number of ight hours. The dataset airline_slr.txt
is available on Learn and contains data for

STAT 331/SYDE 334 (W12) Assignment #4
(Due Thursday, March 22, in class)
1) [8] (Please note: We will not be discussing this concept in lectures. For reference, please consult page 205
of the text)
Recall from Assignment #3 that we applied a square root t

STAT 331/SYDE 334 (W12) Assignment #5
SOLUTIONS
(Due Monday, April 2 in M3 2001, but assignments will be accepted without penalty up until Thursday, April 5
at noon)
Consider the following data from Exercise 9.1 of the text on the relationship between age

STAT 331: Applied Linear Models
Module V Model Selection
version: 2016-09-10 12:38:54
1. Basic Principles of Model Selection
iid
Consider the following problem. We have data Y = (y1 , . . . , yn ) such that yi f0 (y) are iid
observations from some unknown