Intensive 5 ECTS PhD course in August 2014 - Department of Economics and Business, Aarhus University
6302: Economic Modeling and Inference - lectured by Bent Jesper Christensen - course page: http://kursuskatalog.au.dk/en/coursecatalog/Course/show/48812/
Main reading: Christensen and Kiefer: Economic Modeling and Inference, Princeton University Press 2009, http://press.princeton.edu/titles/8903.html
There will be a separate registration period for this course in the period 3 - 16 March 2014. All students who wish to attend the course must register via the self-service facility.
If you are an international PhD or Master's student interested in the course, please send an email to Louise Søe: [log in to unmask]
Course Contents:
The course covers identification and estimation of stochastic dynamic programming models. Sources of error (measurement error, imperfect control, random utility) are treated. Applications are drawn from macroeconomics, labor, finance, marketing, and applied microeconomics. The lectures include occasional discussions of exercises.
Subject areas treated:
Stochastic dynamic programming in discrete and continuous time
Estimation of dynamic programming models by maximum likelihood and GMM
Measurement error, imperfect control, random utility
Finite and infinite horizon, discrete and continuous states and controls
Macroeconomic applications: Consumption, labor demand and supply, asset pricing, time to build, time inconsistency of optimal plans, money
Labor applications: Job search, retirement, wage distribution, unemployment, absenteeism, schooling and occupational choice
Finance applications: Option pricing, portfolio choice, hedging, asset allocation, term structure analysis, stochastic volatility and jumps, volatility forecasting
Marketing applications: Advertising campaigns, cost of price adjustments, direct mailing of catalogs, purchase histories
Microeconomic applications: Patents, engine maintenance and replacement, fertility and child mortality, scrapping subsidies
Econometrics: Cross-section, time series, and panel data methods
|