University of Kansas Philip A. Schrodt
Political Science 907 Blake Hall 523, 864-3523
Spring 1998 Office hours: M1-4,T9-11

Political Science 907
Quantitative Research Methods in International Studies

Course Description

This course is a practical introduction to contemporary quantitative research methods in international politics. It will emphasize hands-on exercises with the data and some of the techniques most commonly used in international politics, as well as with the problems of research design, modelling and testing hypotheses about international behavior. Topics include practical issues in regression analysis; computer programming, dynamic modeling, event data and content analysis, time series techniques, and classification methods such as cluster analysis.

Prerequisites:

Political Science 707 or equivalent. The course is primarily intended for students who will be doing Ph.D.-level research in international politics but should also be of interest to students studying political methodology.

Texts:

None required; you will need to buy a book on C programming for the first section. All readings listed will be available in the Allen Room in the "POLS 907" folders.

Comments on readings:

1. The "Additional" readings are mostly texts and reference works relevant to the topic, along with some examples of applications.

2. The readings over-sample from the works of P. Schrodt. This does not mean these works are the finest available in political science, merely that their mode of presentation tends to be compatible with how I teach. When you prepare your own syllabi, I would expect you to be less dependent on the works of this author.

Evaluation:

Course grade will be based on the completion of an assortment of homework exercises; these will be approximately bi-weekly. Attendance will not be taken on the assumption that since you are Ph.D. students, you consider this endevour a full time job, and therefore will attend class. Significant departures from this pattern will be viewed with utmost disfavor. Assignments should be done on time: even in the academic world some deadlines -- notably conference papers -- are real and close is not good enough. Get in practice. This class also moves fairly quickly across different topics, and it will be difficult to catch up if you fall behind. In particular a number of the later assignments require mastery of the basic computer programming skills taught in weeks 2-4.

Pedagogy

Political methodology is primarily learned by doing, not reading, and therefore this class will focus on practical exercises and techniques rather than the extensive study of texts. Articles presenting original research -- there are a number of these in the required readings -- can also be expected to take some time to understand, so don't attempt to skim them at the last minute.

There is no research paper required in the course but several of the exercises will be fairly time-consuming. Because this is the most advanced methodology course we offer, some of the data sets used in exercises will be presented in "as is" condition (i.e. as I received them): lousy documentation, unknown codes, unexplained missing cases etc. You should cope with these using your best professional judgement; I'll be available for advice but not hand-holding. Most exercises will be fairly open-ended: I will typically give you a data set and ask you to explore a plausible hypothesis of your own creation using a particular method, rather than asking you to test a specific hypothesis. If you would like to work with a data set other than the one I provide in class, you are welcome to substitute it assuming it contains variables appropriate to the methods we are studying.

COURSE TOPICS, EXERCISES AND READING ASSIGNMENTS

Week 1: Introduction (13 January)
Survey of the class, discussion of the general teaching and research approach

Readings:

Review material on basic research design from 706 and 707: go back and actually re-read it, and try to work out how much is really relevant when dealing with international relations rather than survey research. Then for a more cautionary and/or countervailing perspective, read:

Eckstein, Harry. "Case Study and Theory in Political Science" in Fred I. Greenstein and Nelson W. Polsby. 1975. Handbook of Political Science: Strategies of Inquiry. Addison-Wesley

Most, Benjamin A. and Harvey Starr, "Foreign Policy Substitution and 'Nice' Laws", chpt 5 in Most and Starr, Inquiry, Logic and International Politics (South Carolina University Press, 1989)

Bull, Hedley. International Theory: The Case for the Classical Approach. World Politics 18: 361-378.

Donald N. McClosky. "The Rhetoric of Significance Tests", chapter 9 in McCloskey, The Rhetoric of Economics (University of Wisconsin Press, 1985)

Exercise:

Find an article in international relations or comparative politics which you think is flawed because of the research design; make a copy of same and be prepared to discuss it in class.

Additional:

General remarks on bibliography: The primary journals featuring quantitative and modeling research in international relations -- beyond the basic crosstabulation/regression approach -- are International Studies Quarterly, Journal of Conflict Resolution and International Interactions. The American Journal of Political Science and American Political Science Review are also good sources; AJPS publishes very little IR but its Workshop sections provide excellent overviews of newer techniques. Over the past decade World Politics has begun to publish some quantitative work, and an assortment of smaller specialized journals -- for example Conflict Management and Peace Science -- feature a variety of articles on formal methods.

Weeks 2-5 (20 January -- 10 February) Computer Programming

Readings:

At the Oread Bookstore, Borders or wherever, find a book that you like on C -- there are literally dozens. Buy it; read it. These books differ substantially in the order that they present material (itself an interesting observation) but the core material in all of them is the same. ANSI C is a standardized language and a program written in ANSI C will compile and run on a Windows, Macintosh or Unix system without modification.

Additional:

With the ascendency of personal computer, the literature on computer programming has grown exponentially. The Oread Bookstore in the Union has two aisles worth; Borders Books has at least twice that. Browse. The following are a few reference books on algorithms; if you are dealing with a standard operation -- sorting, indexing, graphics , minimizing a function, generating random numbers -- it is a good idea to check some standard references, since the most efficient algorithms are usually anything but obvious. If you are embarking on a large project, it is also worthwhile to consult some works on software development: the amount of time a given project takes can vary by a factor of 20 or more depending on its planning, so investing time in study will pay off in reduced time debugging.

Week 6: ( 17 February)
Review of basic regression and exploratory data analysis

Readings:

Review everything you've read and forgotten about multiple regression from POLS 706 and 707. The focus of the class will be going over the interpretation of a regression analysis and the various things that can go wrong with it.

WARNING:Past experience with this exercise has demonstrated that the level of retention of this material is quite low; to minimize the level of humilitation, review it.

King, Gary. 1986. How Not to Lie with Statistics. American Journal of Political Science 30,3: 666-687.

Additional:

Week 7 ( 24 February)
Univariate Dynamic Models and Chaos

Readings:

Schrodt, "Dynamic Models" chapter

L. Douglas Kiel and Euel Elliott. 1996. Chaos Theory in the Social Sciences. Ann Arbor: University of Michigan Press. Introduction; Chapter 1, 2, and 7

Additional

General references on difference equations

Chaos:

Week 8 (3 March)
Dynamic Models: Systems

Readings:

Schrodt, "Dynamic Systems" chapter.

Francisco, Ronald A. 1996. "Coercion and Protest: An Empirical Evaluation in Two Democratic States" American Journal of Political Science 40,4: 1179-1204

Optional Review: J. Johnston. 1972. Econometrics. New York: McGraw-Hill. Chapter 4 (linear algebra)

Additional:

Note: The general books on difference equations cited above also deal with systems.

Week 9 (10 March)
Introduction to Time Series Analysis

Readings:

Gottman, John M.. 1981. Time-Series Analysis: A Comprehensive Introduction for Social Scientists. Cambridge: Cambridge University Press. Chapters 1-11

Additional:

General books on time series [this is just a sample]

Week 10 (17 March)
Time Series Analysis: Tests of Causality

Readings:

Enders, Walter and Todd Sandler. 1993. "The Effectiveness of Antiterrorism Policies: A Vector-Autoregression-Intervention Analysis." American Political Science Review 87:829-844.

Freeman, John. 1983. "Granger Causality and Time Series Analysis of Political Relationships". American Journal of Political Science. 27,2:327-358

Freeman, John R, John T. Williams and Tse-Min Lin. 1989. Vector Autoregression and the Study of Politics." American Journal of Political Science. 33:825-841

Kinsella, David. 1994. "Conflict in Context: Arms Transfers and Third World Rivalries during the Cold War." American Journal of Political Science. 38,3:557-581

[just skim the next two...]

Sheehan ,Richard G. and Robin Grieves. 1982. "Sunspots and Cycles: A Test of Causation". Southern Economic Journal (January 1982):775-777. [statistical demonstration that business cycles cause sunspots]

Thurman, Walter N. and Mark E. Fisher. 1988. Chickens, Eggs and Causality, or Which Came First? American Journal of Agricultural Economics 70(2):237-238.[statistical demonstration that eggs cause chickens but not vice versa]

Additional:

-------- SPRING AND ISA BREAK --------

Week 11 (31 March)
KEDS and Event Data Analysis

Readings:

Schrodt, Philip A. and Deborah J. Gerner. 1998. The Analysis of International Event Data. (unpublished manuscript) Chapters 1 and 2.

Laurence, Edward J. 1990. "Events Data and Policy Analysis." Policy Sciences 23:111-132.

Leng, Russell J. and J. David Singer. 1988. "Militarized Interactive Crisises: The BCOW Typology and Its Applications." International Studies Quarterly 32:155-1174.

Additional:

Week 12 (7 April)
Content Analysis

Readings:

Weber, Robert Philip. 1990. Basic Content Analysis. Newbury Park: Sage.

Walker, Stephen, Mark Schafer and Michael D. Young. 1998. "Systematic Procedures for Operational Code Analysis: Measuring and Modeling Jimmy Carter's Operational Code." International Studies Quarterly 42, 175-190.

Blanton, Shannon Lindsey. 1996. "Images in Conflict: The Case of Ronald Reagan and El Salvador." International Studies Quarterly 40, 23-44.

Additional:

Weber has an extensive bibliography of the classic human-coded content analysis methods.

For a current overview of the machine-coding software, William Evans at Georgia State has assembled a very nice set of pointers to most of the available programs: http://www.gsu.edu/~wwwcom/content.html

The following books provide useful overviews of the general topic of text processing; these techniques go well beyond content analysis

Week 13: (6 April)
Cluster analysis and nearest-neighbor techniques

Readings:

Everitt, Brian. 1980. Cluster Analysis (2nd ed.) New York:Wiley/Halsted. pp. 1-58 [just read for the concepts; don't try to get all of the math]

Schrodt, Patterns, Rules and Learning, chapter 5, section on nearest neighbor methods

Schrodt, Philip A. and Deborah J. Gerner. 1996. "Using Cluster Analysis to Derive Early Warning Indicators for Political Change in the Middle East, 1979-1996." Paper presented at the American Political Science Association meetings.

Additional:

Week 14 (21 April)
Event History Analysis and Sequence Analysis Methods

Readings:

Janet M. Box-Steffensmeier and Bradford S. Jones. "Time is of the Essence: Event History Models in Political Science. American Journal of Political Science 41,4:1414-1461

King, Gary. 1989. "Event Count Models for International Relations: Generalizations and Applications" International Studies Quarterly 33(2):123-148.

Schrodt, Philip A. and Deborah J. Gerner. 1998. The Analysis of International Event Data. (unpublished manuscript) Chapter 5 (hidden Markov models).

Additional:

Week 15 (28 April)
Survival Skills

Readings:

Wilkinson, Leland. 1989. "Cognitive science and graphic design" chapter in SYGRAPH: The System for Graphics. Evanston, IL: SYSTAT,Inc.

Carlson, Maria. n.d. "Submitting a Grant Proposal". manuscript, University of Kansas Center for Russian and East European Studies.

Schrodt, Philip A. and Deborah J. Gerner. 1994. "NSF Proposal: Development of Machine-Coded Event Data Techniques for the Analysis of Political Behavior".
[okay, it's that Schrodt guy again. But in our defense, KU uses this in their grant-writing workshops for junior faculty as an example of how to write a good proposal. And the bottom line: it was funded!]

RAND Corporation. 1996. "Guideline for Preparing Briefings". Santa Monica, CA: Communications Consulting Group, RAND.

National Science Foundation. 1997. "Grant Proposal Guide" Chapter 2.

Additional:

Statistical Graphics

Wilkinson has an extensive bibliography of articles; the key thing to keep in mind is that good statistical graphics are carefully designed based on the characteristics of human visual perception; they don't simply arise by luck (bad statistical graphics can also be carefully designed: consult any issue of USA Today or Time). You might also find it useful to browse a couple of books on basic graphical design; the bookstore has dozens of them in the art section.