Syllabus
– Draft
Advanced Topics -- Building and Testing Mathematical
Models
PS 299 / Tu Th 2:50PM - 4:05PM Perkins 307
Scott de Marchi
409 Perkins
Director, Program for Advanced Research in the Social
Sciences
Assoc. Prof., Dept. of Political Science
Duke University
(919) 660-4342 [office]
(919) 304-4907 [home]
Michael
Munger
408 Perkins
Chair, Political Science Department
(919) 660-4300 [office]
(919) 369-6453 [cell]
Summary.
Empirical
Implications of Theoretical Models (EITM), for many social scientists, involves
developing a correspondence between game theory (i.e., the theoretical models
half of the acronym) and parametric statistical work (i.e., the empirical
implications half). Implicit in this formulation is the idea that game
theory, as an encoding, represents rational play, and can accommodate most
phenomena of interest. The challenge is that many game theoretic models
lack clear empirical referents; thus, better tools are needed to test the
results of these models. This approach to EITM is certainly useful, but
will not be the only focus of this course.
Instead,
we will be taking the road less traveled. For us, theoretical models will
be considered more broadly, borrowing from the social choice tradition,
computational political economy, as well as game theory. The main goal of the course will be to
consider how to state a "good" theory in the first place, and
consider what types of analytic and statistical methods are required to answer
them.
Readings + Themes.
i. Week
1: Background on the debate; what is EITM.
Tuesday August 26:
·
Aldrich, Alt, and
Lupia.
Forthcoming. The EITM Approach: Origins and Interpretations.
·
NSF Political
Science Directorate. 2002. The NSF EITM Report.
Thursday August 28:
·
Walt, Stephen.
1999. ‘Rigor or Rigor Mortis?’ International Security, 23: 5-48. A forum
followed which includes: Bueno de Mesquita,
Bruce and James Morrow. 1999. ‘Sorting Through the Wealth of Notions.’
International Security, 24: 56-73. Niou, Emerson and
Peter Ordeshook. 1999. ‘Return of the Luddites.’ International Security, 24:
84-96. Powell, Robert. 1999. ‘The Modeling Enterprise and Security Studies.’
International Security, 24: 97-106. Walt, Stephen. 1999. ‘A Model
Disagreement.’ International Security, 24: 115-130.
ii.
Weeks 2-3: Examples of models + tests.
Tuesday September 2:
·
Denzau, Arthur
T., and Michael C. Munger. "Legislators and Interest-Groups: How
Unorganized Interests Get Represented." (1986): 89-106.
·
Hall, Richard L.,
and Frank W. Wayman. "Buying Time: Moneyed
Interests and the Mobilization of Bias in Congressional Committees."
(1990): 797-820.
Thursday September 4:
·
William Riker and
Peter Ordeshook,
“A Theory of the Calculus of. Voting,” American Political Science Review, 62:1
(1968)
25–42.
·
Aldrich, John H. 1993. “Rational Choice and Turnout.” AJPS 37: 246-78.
·
Cox,
Gary, Munger, Michael. “Closeness Expenditures and
Turnout in 1982 House Elections.” The American Political Science Review, 1989.
·
Fort,
Rodney.
1995. "A Recursive Treatment of the Hurdles to Voting". Public Choice
85: 45-69.
Tuesday Sept 9:
Thursday
Sept 11:
·
Fair, Ray C.
“Interpreting the Predictive Uncertainty of Elections,” forthcoming, JOP 2009
·
Fair model site, with estimates
iii.
Week 4: An overview of a bunch of things (computational political economy,
non-parametric models, etc.).
Tuesday Sept 16:
·
de Marchi, Scott.
Lifting the Curse of Dimensionality: Computational Modeling in the Social
Sciences. Chapters 1-3.
Thursday
Sept 18:
·
Using
statistics, misusing statistics
First Assignment (due Oct. 31 by Midnight).
(1) Write
a model that would predict the outcome (% for each candidate) in upcoming
presidential race between McCain and Obama.
For a baseline, take a look at Ray Fair's model (http://fairmodel.econ.yale.edu/vote2008/index2.htm). Data is also available at his site.
(2)
Gather historical data (>= 1 previous presidential race) to see how your
model does in comparison to the actual results.
(3) Gather
the data and generate a prediction from your model.