Chapter 10: Validation of Regression Models
Before the model is released to the user, some assessment of its validity should be made.
We distinguish between model adequacy checking and model validation. Model
adequacy checking includes residual analysis,
STAT 378 Applied Regression Analysis
Fall 2015
Assignment 2: (Due date is Oct 9, 2015 by 10:00am)
1) Please write legibly or type your answers.
2) Please supply the R code that you use to do the data analysis. You should write
your answers so that the rel
STAT 378 Applied Regression Analysis
Fall 2015
Assignment 1: (Due date is September 23, 2015 by 10:00am)
1) Please write legibly or type your answers.
2) Please supply the R code that you use to do the data analysis. You should write
your answers so that
STAT 378 Applied Regression Analysis
Fall 2015
Assignment 4: (Due date is Nov 23, 2015 by 5:00pm)
1) Please write legibly or type your answers.
2) Please supply the R code that you use to do the data analysis. You should write
your answers so that the rel
STAT 378 Applied Regression Analysis
Fall 2015
Assignment 3: (Due date is Nov 6, 2015 by 5:00pm)
1) Please write legibly or type your answers.
2) Please supply the R code that you use to do the data analysis. You should write
your answers so that the rele
Subject 2 Transformation for Simple Linear
Regression
STAT 429, Fall 2014
Instructor: Bingrui (Cindy) Sun
Textbook:
A Modern Approach to Regression
with R by Simon Sheather Chapter 3
Outline
2.1 Overcome Problems Due to Nonconstant Variance
2.2 Overcome P
Solution of Assignment #1
Instructor: A. Simchi
Question #1:
(a) The scatter plots are given on the computer output on pages 1 and 2. The
least-square estimate of the regression line when DI regressed on IQ is
DI = 52.2729 0.2489 IQ
(b) The scatter plot,
Chapter 4: Model Adequacy Checking
In this chapter, we discuss some introductory aspect of model adequacy checking,
including:
Residual Analysis,
Residual plots,
Detection and treatment of outliers,
The PRESS statistic
Testing for lack of fit.
The major a
Chapter 9: Variable Selection and Model Building
In this chapter, we will talk about:
Variable selection and model building problem,
Several criteria for the evaluation of subset regression models,
All possible regressions procedure,
Backward Elimination
Chapters 2 and 3: Simple and Multiple Linear Regressions
This chapter provides the standard results for least-square model fitting in the multiple
linear regressions. In this chapter, we will talk, in a multiple regression model, about
Estimation of the M
Solution of Assignment #7
Instructor: A. Simchi
Question #1:
(a) The least-square line of SBP (Y ) on QUET (X) for Smokers and nonsmokers
are:
Non smokers : SBP = 49.312 + 26.303 QU ET
Smokers : SBP = 79.255 + 20.118 QU ET
(b) Let The single multiple mode
Chapter1: Introduction
Chapter 1 is a general introduction to regression modeling, and describes some typical
application of regression.
The purpose of most research is to assess relation among a set of variables.
Definition: If the variable under investi
Solution of Assignment #2
Instructor: A. Simchi
Question #1:
(a) The least-square estimate of the regression line when Y regressed on X is:
Y = 1.69956 + 0.83991 X
The change in the mean response when X increases by one unit is just 1 .
Therefore, the est
Solution of Assignment #3
Instructor: A. Simchi
Question #1:
(a) The least-square estimate of the regression line when systolic blood pressure
(Y ) regressed on weight (X) is:
Y = 69.10437 + 0.41942 X
(b) Based on the computer output on page 1, we have
An
Solution of Assignment #6
Instructor: A. Simchi
Question #1:
(a) The plot of Y versus X is given on page 1 of SAS output. It is clear that a
straight line model is not adequate. By looking at the graph, it seems that the
1
transformation X or ln(X) is mor
Solution of Assignment #5
Instructor: A. Simchi
Question #1:
(a)
(i) The overall F -test is:
TS =
M Sr (X1 )
1535.85697
=
= 6.39
M SRes (X1 )
240.30025
Since p value = P (T S > 6.39) = 0.0146 < = 0.05, we reject H0 : 1 = 0
versus H1 : 1 = 0. Therefore X1
Solution of Assignment #4
Instructor: A. Simchi
Question #1:
(a) The least-square estimate of the regression line when Y regressed on X1 is:
Y = 70.42020 + 227.09370 X1
Based on the computer output on pages 1 and 2, we have R2 = 0.9194 and
2
rY X1 = 0.958
University of Alberta
Department of Mathematical & Statistical Sciences
Statistics 378* Section S1
Fall 2015
Instructor:
Office:
Phone:
E-mail:
Subhash R. Lele
CAB 423
780 492 4290
slele @ualberta.ca
Office Hours:
Tuesdays: 10:00-11:00am, Fridays: 4:00-5: