Professor Schneider
324B S. Kedzie Hall
sks@msu.edu
517/355-7682
PLS 802
Spring 2010
REGRESSION ANALYSIS
This course provides an introduction to the theory, methods, and practice of regression analysis.
The goals are to provide students with the skills that are necessary to: (1) read, understand, and
evaluate the professional literature that uses regression analysis; (2) design and carry out studies
that employ regression techniques for testing substantive theories; and (3) prepare to learn about
more advanced statistical procedures.
The course will not dwell on statistical theory, but it will also not take a superficial approach.
Instead, it will focus on: The utility of regression analysis for evaluating empirical relationships
between variables as a critical component of the theory-testing process. We will thoroughly
cover the basic elements of the regression model and the development of the regression
estimators. We will see that this model depends very heavily on several assumptions. Therefore,
we will examine these assumptions in detail, considering why they are necessary, whether they
are valid in practical research situations, and the consequences of violating them in particular
applications of the regression techniques. These formal, analytic treatments will be
counterbalanced by the use of frequent substantive examples and class exercises. Again, the
overall course objective is not to turn you into a statistician– instead, the aim is to maximize
your research skills as a political scientist.
Course Prerequisites: Any course of this type must assume a working knowledge of
elementary statistical concepts and techniques. We will conduct a brief review at the beginning
of the course, but students must be familiar with such ideas as descriptive statistics, sampling
distributions, statistical inference, confidence intervals, and hypothesis testing, before moving on
to the more complicated matters that will comprise the majority of the course material. You must
have completed at least one prior course in introductory statistics course– i.e., PLS 801 or the
equivalent.
Course Requirements: Formal course requirements are as follows: (1) Class attendance and
active participation. This is mandatory. Statistical knowledge is cumulative, and gaps in the
material will have detrimental consequences. (2) Completion of homework assignments. Most of
these are computer-based data analysis exercises, designed to familiarize you with the
application of various concepts and techniques. Each of these assignments will focus on a
specific set of topics. However, the latter assignments are cumulative in the sense that they build
upon earlier material in the class. Homework assignments will be given frequently (about once a
week or so). They will not be assigned grades, but they will be checked for completion and
comments will be provided to make sure that you fully understand the material. (3) Two
examinations. A mid-term examination will be given in class on Wednesday, March 3; the final
will be a take-home examination, due on Wednesday, May 5, 2010 at 5:00 p.m.
PLS 802, Spring 2010
Page 2
Assignment of Final Grades:
Homework Assignments & Class Participation
Midterm Examination
Final Examination
30 %
30 %
40 %
Textbooks:
The following are the main required texts for the course:
*
Gujarati, Damodar N., and Dawn C. Porter. 2009. Basic Econometrics (Fifth Edition).
Boston, MA: McGraw-Hill.
OR
*
McClendon, McKee. 1994 (reissued 2002). Multiple Regression and Causal Analysis.
Prospect Heights, IL: Waveland Press.
You should select either Gujarati or McClendon as your main required text.
In addition, we will rely upon material from the following two other required books:
*
Berry, William D., and Stanley Feldman. 1985. Multiple Regression in Practice.
Beverly Hills, CA: Sage Publications.
*
Fox, John. Regression Diagnostics.1991. Beverly Hills, CA: Sage Publications.
The following books are useful recommended books; they provide more detailed,
comprehensive coverage of the material along with explicit derivations of statistical concepts. If
you plan on taking additional methods courses, you should acquire one of these books:
Kennedy, Peter. 2008. A Guide to Econometrics (Sixth Edition), Malden, MA: Black
Publishing, Inc.
Wooldridge, Jeffrey M. 2006. Introductory Econometrics: A Modern Approach (Third
Edition). Mason, OH: Thomson South-Western.
PLS 802, Spring 2010
Page 3
The following books are useful supplemental books; they provide more basic explanations of
key terms and concepts:
Berry, William D. 1993. Understanding Regression Assumptions. Beverly Hills, CA:
Sage Publications.
Lewis-Beck, Michael. 1980. Applied Regression. Beverly Hills, Sage Publications.
Schroeder, Larry D., David L. Sjoquist, and Paula E. Stephan. 1986. Understanding
Regression Analysis: An Introductory Guide. Newbury Park: Sage Publications.
You should read all the designated material assigned in the required texts. You should also have
access to a basic statistics book to help you review statistical concepts and principles, and to
provide reasonable alternative discussions of the bivariate and multiple regression models. Most
of the recommended and supplemental books are either too advanced or elementary to be used as
central texts in this course. However, several of them are very good and would be extremely
useful books for you to rely upon for greater detail or additional explanations at various points in
the course.
Computing and Software: Computers and statistical software are absolutely necessary for
employing modern statistical techniques in an effective manner. Therefore, they will be closely
integrated into the course material. We will use STATA for most of the class examples,
assignments, and examinations. But, you can also use other statistical software in this course
(e.g., R, SAS, SPSS, SYSTAT, etc.), as long as it has the analytical routines and capacities that
are required to complete the assignments and examinations.
If you are not comfortable using STATA, there are a number of books which can help. These
include:
Acock, Alan, C. 2008. A Gentle Introduction to Stata (Second Edition). College Station,
TX: Stata Corporation.
Adkins, Lee, and Carter Hill. 2009. Using Stata for Principles of Econometrics (Third
Edition). New York: Wiley.
Kohler, Ulrich, and Frauke Kreuter. 2009. Data Analysis Using Stata (Second Edition).
College Station, TX: Stata Corporation.
Hamilton, Lawrence. 2009. Statistics with Stata. Cengage.
You are not required to purchase these books, but you might find them helpful in your efforts to
learn and use STATA.
PLS 802, Spring 2010
Page 4
Topics and Reading Assignments
I.
Introduction to Regression Analysis
Reading:
Gujarati, pp. 15-33
McClendon, pp. 1-19
Kennedy, pp. 1-10
Wooldridge, pp. 1-19
II.
Preliminary Material and Statistical Review
A. Frequency Distributions, Univariate Summary Statistics, Probability
Distributions
Reading:
Gujarati, pp. 801-823
McClendon, pp. 20-25
B. Statistical Inference and the Properties of Statistical Estimators
Reading:
Gujarati, pp. 823-837
1. Confidence Intervals & Hypothesis Tests
2. Differences Between Two Means, Two Variances, Etc.
III.
Basic Concepts for Understanding Regression Analysis: Functional
Dependence, Linear Transformations, and Linear Combinations
Reading:
McClendon, pp. 25-28
Wooldridge, pp 707-802
IV.
The Bivariate Regression Model
A. Introduction: Basic Ideas and Concepts
Reading:
Gujarati, pp. 34-54
McClendon, pp. 28-30
Berry, pp. 1-22
PLS 802, Spring 2010
Page 5
B. The Least Squares Criterion and Estimation in the Bivariate Regression
Model
Reading:
Gujarati, pp. 55-73
McClendon, pp.31-41
Berry and Feldman, pp. 9-12
Kennedy, pp. 11-59
Wooldridge, pp. 50-66, 89-95, 106-109, 123-126, 176-181, 187-190
C. Goodness of fit, the Correlation Coefficient and R2
Reading:
Gujarati, pp. 73-92
McClendon, pp. 42-49
Schroeder, Sjoquist, and Stephan, pp. 23-29
D. Assumptions Underlying the Bivariate Linear Regression Model
Reading:
Gujarati, pp. 61-69; 97-101
McClendon, pp. 133-146
Berry and Feldman, pp. 9-12
Kennedy, pp. 11-59
Wooldridge, pp. 50-66, 89-95, 106-109, 123-126, 176-181, 187-190
E. Statistical Inference, Confidence Intervals, and Hypothesis Tests
Reading:
Gujarati, pp. 107-146
McClendon, pp. 147-154
Lewis-Beck, pp. 26-47
Schroeder, Sjoquist, and Stephan, pp. 36-53
Kennedy, pp. 51-90
Wooldridge, pp. 126-147
F. Summary, Extensions, and a Preliminary Look at Residuals, Outliers,
and Influential Cases
Reading:
Gujarati, pp. 147-187
McClendon, pp. 49-59
Berry, pp. 22-88
PLS 802, Spring 2010
Page 6
V.
The Multiple Regression Model
A. Introduction: Notation, Assumptions, and Interpretation
Reading:
Gujarati, pp. 188-196; 213-227
McClendon, pp. 60-80
Berry and Feldman, pp. 9-18
Wooldridge, pp. 73-88
B. Measures of Goodness of Fit
Reading:
Gujarati, pp. 196-209
McClendon, pp. 80-83
Schroeder, Sjoquist, and Stephan, pp. 32-36
C. Statistical Inference and the Role of Hypothesis Testing
Reading:
Gujarati, pp. 233-259
McClendon, pp. 133-174
Berry and Feldman, pp. 12-18
Kennedy, pp. 60-80
Wooldridge, pp. 147-167, 214-218
D. Models of Substantive
Assumptions
Reading:
Phenomena;
McClendon, pp. 83-93, 154-157
Berry, pp. 1-24
Lewis-Beck, pp. 63-66
E. Summary and a Brief Look at Extensions
Reading:
Gujarati, pp. 259-276
McClendon, pp. 93-118
(McClendon, pp. 119-132)
The
Importance
of
Model
PLS 802, Spring 2010
Page 7
VI.
Model Building in Multiple Regression Analysis
A. Model Specification
Reading:
Gujarati, pp. 467-522
McClendon, pp. 288-321
Berry and Feldman, pp. 18-26
Berry, pp. 30-45
Kennedy, pp. 71-92
Lewis-Beck, pp. 30-45
Schroeder, Sjoquist, and Stephan, pp. 67-70
B. Functional Forms, Nonlinearity and Transformations
Reading:
Gujarati, pp. 525-540
McClendon, pp. 230-270
Berry and Feldman, pp. 51-72
Berry, pp. 60-66
Kennedy, pp. 93-111
Schroeder, Sjoguist, and Stephan, pp. 58-61
Wooldridge, pp. 304-310
C. Nominal Independent Variables
Reading:
Gujarati, pp. 277-314
McClendon, pp. 198-229; 271-287
Kennedy, pp. 248-258
Schroeder, Sjoquist, and Stephan, pp. 56-58
Wooldridge, pp. 230-252
PLS 802, Spring 2010
Page 8
VII.
Potential Problems in Multiple Regression Analysis
A. Interpretation of Results
Reading:
Fox, pp.3-5
B. Multicollinearity and Its Effects
Reading:
Gujarati, pp. 320-364
McClendon, pp. 161-163
Berry and Feldman, pp. 37-50
Fox, pp. 10-21
Berry, pp. 24-27
Kennedy, pp. 192-202
Lewis-Beck, pp. 58-63
Schroeder, Sjoquist, and Stephan, pp. 71-72
Wooldridge, pp. 101-105
C. Nonnormal and Nonconstant (Heteroscedastic) Errors
Reading:
Gujarati, pp. 365-411
McClendon, pp. 174-197
Berry and Feldman, pp. 73-88
Fox, pp. 40-53
Berry, pp. 67, 72-81
Kennedy, pp. 133-139
Wooldridge, pp. 181-185
D. Measurement Error
Reading:
Gujarati, pp. 482-485
Berry and Feldman, pp. 26-37
Berry, pp. 45-60
Kennedy, pp. 157-163
Schroeder, Sjoquist, and Stephan, pp. 70-71
Wooldridge, pp. 318-325
PLS 802, Spring 2010
Page 9
E. Residual Analysis, Outliers, and Influential Observations
Reading:
Fox, pp. 21-40
Berry, pp. 27-29
Kennedy, pp. 372-388
VIII.
Additional Topics
A. Dichotomous Dependent Variables
Reading:
Gujarati, pp. 541-590
Schroeder, Sjoquist, and Stephan, pp. 79-80
Wooldridge, pp. 252-258
B. Simultaneous Equation Models
Reading:
Gujarati, pp. 673-736
McClendon, pp. 288-347
Berry, pp. 1-54
Schroeder, Sjoquist, and Stephan, pp. 77-79
C. Nonindependent Disturbances and Time Series Models
Reading:
Gujarati, pp. 737-800
Berry, pp. 67-72
Kennedy, pp. 139-156, 163-179
Schroeder, Sjoquist, and Stephan, pp. 72-75