Go to main navigation Navigation menu Skip navigation Home page Search

Higher Seminar in Economics | Imposing equilibrium restrictions in the estimation of dynamic discrete games

Department of Economics is welcoming you to online seminar with Mathieu Marcoux, Assistant Professor of Economics, Université de Montréal. We study the asymptotic properties of the NPL algorithm treating the iterative procedure as performed in finite samples. We find that there are always samples for which the algorithm fails to converge, and this introduces a selection bias. We also propose a spectral algorithm to compute the NPL estimator. This algorithm satisfies local convergence and avoids the approximation of Jacobian matrices. We present simulation evidence illustrating our theoretical results and the good properties of the spectral algorithm. This is an online seminar which will take place via Zoom.

Welcome to Higher Seminar in Economics organised by the Department of Economics, SSE. The seminar speaker is Mathieu Marcoux, Assistant Professor of Economics, Université de Montréal.

"Imposing equilibrium restrictions in the estimation of dynamic discrete games", joint work with Victor Aguirregabiria

Abstract

Imposing equilibrium restrictions provides substantial gains in the estimation of dynamic discrete games. Estimation algorithms imposing these restrictions have different merits and limitations. Algorithms that guarantee local convergence typically require the approximation of high-dimensional Jacobians. Alternatively, the Nested Pseudo Likelihood (NPL) algorithm avoids the computation of these matrices, but – in games – may fail to converge to the consistent NPL estimator. We study the asymptotic properties of the NPL algorithm treating the iterative procedure as performed in finite samples. We find that there are always samples for which the algorithm fails to converge, and this introduces a selection bias. We also propose a spectral algorithm to compute the NPL estimator. This algorithm satisfies local convergence and avoids the approximation of Jacobian matrices. We present simulation evidence illustrating our theoretical results and the good properties of the spectral algorithm.

Mathieu Marcoux is an Assistant Professor of Economics - Université de Montréal. Mathieu Marcoux's interests are in econometrics, applied econometrics and industrial organization.

This is an online seminar which will take place via Zoom. The link to the seminar will be distrubted by invitation only. Please contact lyudmila.vafaeva@hhs.se if you would like to attend the seminar.

Dept. of Economics Seminar in economics Webinar

This website uses cookies. By using this website you are agreeing to our use of cookies and to the terms and conditions listed in our data protection policy. Read more