ECONOMICS 950
ADVANCED TOPICS IN
QUANTITATIVE ECONOMIC POLICY ANALYSIS

C. Ferrall
Fall 2002
[Version 1.0]

Objective

This course covers methods required to:

• solve modern economic models numerically
• estimate parameters of a model using sophisticated sources of data
• analyze policy questions using the estimated model

The emphasis is not to teach specific computer programming skills, but rather to help students make smart choices about programming given resources available at Queen's and trends in high performance computing.

Prerequisites

Students are expected to be able to program basic numerical mathematics in Ox or C. For example, by the first meeting on September 10 a student should have completed assignments 1.0, 1.1, and 1.2 from Econ 951 (Winter 2001) or have gained equivalent experience from other work.

Requirements

To audit this course you must

• Participate in class: Tuesdays, 1:00-3:45 PM, Location TBA (note excluded weeks below).
• Participate in Quant Workshops
• Participate in NIEPA September 20-21. (No lecture Sep. 24.)
• [Suggested, not required] Travel to and participate in CESG 2002 October 18-20. (No lecture October 22.)
• [Suggested, not required] Participate in CMSG November 8-9.
• Make a 75 minute in-class presentation of your own work. This requirement is fulfilled by presenting relevant material in a department workshop. The presentation in 950 must be made before a similar presentation in 999 and must be distinct from any earlier 999 presentations.

To get credit for this course you must also:

• Make a 75 minute in-class presentation of a paper on the list below or a mutually agreeable substitute
• Write a program in Ox or C that executes in parallel and correctly computes something useful. The amount of programming expected is not large, and it will be adjusted to the student's programming experience to roughly equalize the amount of work required across students. Group work is highly recommended.

Outline

Student presentations will be scheduled after October.

1. Distributive Processing and Numerical Economics

MPI Primer, Ferrall, Doornik et. al, applications

2. Modelling Exogenous Variation and Policy Innovations

Ferrall, applications

3. Matched Data Sets

Legros and Newman

4. Strategic Environments

Aguirregabiria and Mira, Pakes and McGuire

References and Presentable Papers (to be done, may include papers in the outline)

1. Aguirregabiria, Victor 2002. "Recursive Pseudo Maximum LikelihoodEstimation of Structural Models Involving Fixed-Point Problems," manuscript.
2. Aguirregabiria and Mira, "Identification and Estimation of Dynamic Discrete Games"
3. Aguirreagabiria, Victor and Pedro Mira (2001). "Swapping the Nested Fixed Point Algorithm A Class of Estimators for Discrete Markov Decision Models and Gauss code (hint, hint).
4. Diermeier, Daniel, Eraslan, Hulya and Antonio Merlo 2001. "A Structural Model of Government Formation," accepted for publication, Econometrica.
5. Fang, Hanming 2002. "Disentangling the College Wage Premium: Estimating a Model with Endogenous Education Choices, manuscript.
6. Fang, Hanming and Dan Silverman 2001. ``Time-inconsistency and Welfare Program Participation: Evidence from the NLSY," manuscript.
7. Imai, Susumu, and Neelam Jain and Andrew Ching 2002. Bayesian Estimation of Dynamic Discrete Choice Models with figures
8. Krusell, Per and Burhanettin Kuruscu, and Anthony A. Smith, Jr. "Equilibrium Welfare and Government Policy with Quasi-Geometric Discounting", manuscript.
9. Legros, Patrick and Andrew F. Newman 2002. ``Monotone Matching in Perfect and Imperfect Worlds," accepted for publication, REStud.
10. Moro, Andrea 2002. "The Effect of Statistical Discrimination on Black-White Wage Differentials: Estimating a Model with Multiple Equilibria," forthcoming, International Economic Review.
11. Pakes, Ariel and Paul McGuire 2000. ``Stochastic Algorithms, Symmetric Markov Perfect Equilibrium and the `Curse' of Dimensionality,"