Methods and Statistics in Political Science
Political Science 221

Sections A (CRN 22808), B (CRN 23861), and C (CRN 24404)
Hance Auditorium
Monday, Wednesday, Friday
10:30 – 11:20 p.m.
Spring 2009

Dr. Ken Menkhaus
Chambers 2031
Office phone: 704-894-2291
Email: kemenkhaus@davidson.edu

Dr. Shelley Rigger
Preyer 201B
Office phone: 704-894-2505
Email: shrigger@davidson.edu

Dr. Patrick Sellers
Chambers 2039
Office Phone: 704-894-2078
Email: pasellers@davidson.edu


Office Hours:
M: 11:30-1:00 (Sellers, CHA2039), 11:30-12:30 (Menkhaus, CHA2031)
T: 8:30-10:00 (Rigger, Preyer 201B), 11:00-12:00 (Menkhaus, CHA2031)
W: 4:30-6:30 (Sellers, CHA2039), 11:30-12:30 (Menkhaus, CHA2031)
Th: 2:30-5:00 (Rigger, Preyer 201B), 11:00-12:00 (Menkhaus, CHA2031)
F: 11:30-1:00 (Sellers, CHA2039), 2:00-3:00 (Menkhaus, CHA2031)
And by appointment

Additional
course
materials

 Course Objectives

The world of politics offers a nearly infinite array of interesting and important problems.  Why did George Bush win the 2004 presidential election?  Is Europe's adoption of a common currency a merely superficial change or an important development fundamentally affecting the region's political and economic institutions?  Why is religious fundamentalism thriving in Islamic countries?  For these and many other questions, potential answers may be difficult to sort out.  It is even harder to demonstrate conclusively that one of those answers is more "correct" than another.  This course will help you think more carefully and systematically about political questions, their potential answers, and the types of evidence needed to evaluate those answers.

To encourage such careful, systematic thinking, the course focuses on the analytical framework of social science and statistics.  During the first part of the semester, we explore this framework without using numbers.  We examine how that logic can improve many types of non-quantitative analysis (i.e., research without "number crunching"), from historical analysis to single or comparative case studies.  The social science principles can help make this type of research more logical and systematic.  However, the application of social science principles to non-quantitative work is not universal and can be controversial; we will also discuss some of these controversies.  

During the second part of the semester, we examine the same social science principles in their more common context: statistical analysis with many observations.  With the growing availability of surveys and other large data sets, politicians and political scientists are increasingly turning to this type of analysis.  We begin with a discussion of averages and then move to basic concepts of probability and hypothesis testing.  We conclude with several weeks on correlation and regression, two of the most common types of statistical analysis.  These topics often create fear in the minds of political science majors, particularly those who chose the major in order to avoid all contact with numbers!  This course can alleviate such "stats anxiety."  Students are NOT required to have an extensive background in math or calculus.  Instead, they should understand basic math functions (addition, subtraction, multiplication, and division) and be willing to learn and apply additional math concepts.

Mastery of the course concepts can benefit students in many ways.  Here at Davidson, an understanding of social science and statistical principles can help in other courses by making it easier to understand political science research presented in those courses.  You can impress friends and professors by posing important questions about that research: Why were the particular cases chosen for analysis?  Were these the best cases?  Does the evidence presented persuasively support the author's argument?  The concepts from this course can also make it easier for students to do their own research for seminar papers or honors theses.  Finally, the course can prove helpful after graduation.  In addition to developing their analytical and statistical abilities, students must improve their skills of written and verbal expression and learn a statistical computer program (Stata).  After graduation, these skills can make a student more attractive to potential employers.

Course Requirements

Each student’s grade for the course will be based on several components.  

Lateness policy: Work that is handed in after class on the day an assignment is due will be penalized 1/3 of a grade for each day it is late. If you hand in an A+ paper at noon on the day the paper is due, you will receive an A. But no matter how late a paper is, it is always to your advantage to hand it in. Computer failure is not an acceptable excuse for lateness. Back up your work. If you are having printer trouble, email the assignment as an attachment. Do not assume you have secured our permission for something unless you have spoken to us in person or received an e-mail or voice mail message from us.

Extensions: Please do not ask for extensions because you have “too much work;” everyone does, and it’s unfair to give extensions to those who ask, while those who don’t ask end up with less time to do a good job. Also, no extensions will be granted for extracurricular commitments. Look at your personal schedules in advance, and plan your work accordingly.

Honor Code: Anything you hand in is pledged work. But as a reminder of the honor code's importance, we would like you to write out the honor code in full on the cover sheet of any work you hand in. ("On my honor I pledge that I have neither given nor received help on this work, nor am I aware of any violation on the part of others.") Please make sure you understand the honor code, especially the definition of plagiarism. If you have any questions, doubts, or concerns about any aspect of the honor code, please talk to us. If you are unsure how to cite material used in an essay, please discuss it with us.  

Students must complete the two exams individually.  Students may work together to study for exams, as well as to complete problem sets and daily problems. But, each student must submit his or her individual answers for the problem sets and daily problems. We strongly encourage group effort; working together makes it easier to understand the problem and get the right answer!

Grading: The numerical grade for any assignment turned in may range from outstanding (in the 90-to-100 range) to failing (55 or lower).  Note that the failure to complete and turn in any assignment (problem set, weekly problem, or exam) will result in a numerical grade of 0 for that assignment.  When calculating final course grades, we will calculate the overall numerical averages and convert them to letter grades, where A: >=93; A-: >=90, <93; B+: >=87, <90; B: >=83, <87; etc.

Assigned Readings

The required texts are available for purchase in the bookstore:

We will also read several individual articles and chapters. In the outline below, the name of each author is a hyperlink to the actual article or chapter. We may also add additional articles as the semester progresses; these will also be on electronic reserve. Finally, the course outline also mentions a number of optional readings, denoted as "KKV," which come from a book titled Designing Social Inquiry, by King, Keohane, and Verba. A copy of this book is on reserve in the library.

Course Outline

Date Topic Reading Assignment
Jan. 12
  1. Introduction
   
Jan. 14
  1. Designing your research paper
    1. The scientific method
  • Hill
  • Opt.: KKV, 3-12
Jan. 16
    1. Research question
  • Daily Problem #1 handed in
Jan. 19
Martin Luther King, Jr. Day
Jan. 21
    1. Theory and literature review
 
Jan. 23
    1. Evidence (The thick and the thin)
  • Daily Problem #2 handed in
Jan. 26
  1. Measuring Concepts
    1. Making inferences
  • Daily Problem #3 handed in
Jan. 28
    1. Evaluating inferences
  • Problem Set #1 handed in
Jan. 30
    1. Do governments work well?
 
Feb. 2
  1. Causation
    1. Defining causality
  • P(EPA): 28-47
  • Opt.: KKV, 75-84
Feb. 4
    1. What's necessary for cause and effect?
  • Daily Problem #4 handed in
Feb. 6
    1. Building a causal argument
  • Daily Problem #5 handed in
Feb. 9    
  • Daily Problem #6 handed in
Feb. 11
    1. When do governments reform?
 
Feb. 13
  1. Potential problems
    1. More questions than evidence (indeterminancy)
  • Swarns and Altman
  • Opt.: KKV, 115-123
 
Feb. 16
    1. Random selection and selection bias
  • Daily Problem #7 handed in
Feb. 18
    1. Measurement error
  • P(EPA): 13-15
  • Opt.: KKV, 139-149
  • Daily Problem #8 handed in
Feb. 20
  1. Applications
    1. How should we study transitions to democracy?
  • Problem Set #2 handed in
Feb. 23
Midterm Exam
Feb. 25
  1. Quantitative Analysis With A Single Variable
    1. Central tendency and dispersion
 
Feb. 27
    1. Types of relationships
  • P(EPA): 77-100
  • P(SCPA): 59-62, 85-88
  • Caiazza
 
Mar. 2
Spring Break
Mar 4
Mar. 6
Mar. 9
    1. The Normal Curve
  • R, 176-195
  • P(EPA): 102-116
  • Daily Problem #9 handed in
Mar. 11
    1. The Central Limit Theorem
      1. Sampling Distributions
  • R, 206-215
  • P(EPA): 116-120
  • Daily Problem #10 handed in
Mar. 13
      1. Nominal Variables
  • R, 215-222
  • P(EPA): 120-128
  • Daily Problem #11 handed in
Mar. 16
      1. Sample Problems
   
Mar. 18
    1. Confidence in Your Evidence
      1. Calculating a Confidence Interval
  • R, 237-256
 
Mar. 20
      1. Choosing a Sample Size
  • R, 256-258
  • Daily Problem #12 handed in
Mar. 23
      1. Sample Problems
 
  • Daily Problem #13 handed in
Mar. 25
    1. Testing Your Expectations
      1. Six Steps of a Hypothesis Test
  • R, 267-314
Mar. 27    
  • Daily Problem #14 handed in
Mar. 30
      1. Single-Sample Means Test
  • R, 315-344
  • P(SCPA): 107-111
 
Apr. 1
      1. Large Single-Sample Proportions Test
  • R, 344-367
  • Daily Problem #15 handed in
Apr. 3
  1. Adding Variables and Causation
    1. Comparing Two Means
      1. Independent Samples Difference of Means Test
  • R, 368-382
  • P(EPA): 130-139
  • P(SCPA): 111-116
  • Daily Problem #16 handed in
Apr. 6
      1. Non-Independent (Matched-Pair) Difference of Means Test
  • Daily Problem #17 handed in
Apr. 8
    1. Chi-Squared Test and Correlation
  • R, 468-481, 509-524
  • P(EPA): 139-144, 154-157
  • P(SCPA): 122-128
  • Daily Problem #18 handed in
Apr. 10
    1. Applications
  • Problem Set #3 handed in
Apr. 13
Easter Break
Apr. 15
    1. Regression
      1. The basics
Apr. 17
      1. Predicted values and outliers
  • LB, 19-20, 53-54
 
Apr. 20
      1. Statistical tests
  • LB, 20-25, 30-47, 51-53
  • P(EPA): 157-165
  • Gledhill
 
Apr. 22
      1. Including and excluding variables
  • LB, 56-63
  • Kolata
  • Daily Problem #19 handed in
Apr. 24
      1. Dummy variables and interactive effects
  • LB, 66-71
  • P(EPA): 159-175
  • P(SCPA): 164-167
  • Daily Problem #20 handed in
Apr. 27
      1. Applications
   
Apr. 29
      1. Review
 
  • Problem Set #4 handed in
May 1
Optional Classes
May 4
May 6
May 7
Reading Day
May. 8-13
Final Exams