Econometrics 2


Objective

This course aims to complete the teaching of the first-semester econometrics course in the field of the statistical analysis of individual data. The first part of the course (B. Crépon) is an introduction to simultaneous equations and panel econometrics. These two areas generalise the linear model by considering several equations or several time periods. The second part of the course (X. d’Haultfoeuille) considers discrete or limited dependent variable models. The former are extremely widespread, because most survey data is discrete rather than continuous (activity, unemployment, possession of consumer durables, choice of transport, credit scoring). Limited dependent variable models are applied to selection problems (offers of work, endogenous sample selection).

Planning

  1. Generalised moments method –Definition, convergence, optimality, specification tests, applications to instrumental variables in the heteroscedastic case.
  2. Introduction to panel econometrics– Random effects model, fixed effects model, random effects test. Estimation with weak endogeneity: GMM estimation, overidentification tests, application to autoregressive panels.
  3. Evaluation of public policy –Natural experience. Causal model. Difference in difference estimator.
  4. Binary dependent variable models –Logit and probit models: identification, estimation, model quality, heteroscedasticity and endogeneity problems.
  5. Extension of the dichotomic model– Ordered and unordered polytomics, count models (Poisson models).
  6. Limited dependent variable models– Simple tobic model, selection models: exogenous selection, truncation, generalised selection.

 

Références

AMEMIYA, T. Advanced Econometrics, Basil Blackwell, Oxford, 1989 [28 AME 00 A]CREPON B et N. JACQUEMET Econométrie : Méthode et Applications, de Boeck
GOURIEROUX C. Econométrie des variables qualitatives, 2ème éd., Economica, 1989 [28 GOU 00 A]WOOLDRIDGE, J. Econometric Analysis of Cross Section and Panel Data, 1ère ou 2ème éd., MIT Press, 2002 ou 2010 [28 WOO 00 B]