6 novembre 2018

Heure: 9h
Lieu: DES-2237

Détails supplémentaires

Conférencier(e) :

Invité par : Arthur Silve

Pour ce mardi des Déjeuners de l'économie, la séance sera une spéciale "économétrie structurelle".

Arthur Silve vous propose la lecture de : Measuring the Sensitivity of Parameter Estimates to Estimation Moments, et On the Informativeness of Descriptive Statistics for Structural Estimates, par Isaiah Andrews, Matthew Gentzkow, et Jesse Shapiro.

Ci-dessous le résumé de chaque papier. Attention, il faut prévoir plus de temps que d'habitude pour ces deux lectures !
Comme d'habitude, café et croissants vous sont offerts par le département d'économique.

Measuring the Sensitivity of Parameter Estimates to Estimation Moments
Abstract 1: We propose a local measure of the relationship between parameter estimates and the moments of the data they depend on. Our measure can be computed at negligible cost even for complex structural models. We argue that reporting this measure can increase the transparency of structural estimates, making it easier for readers to predict the way violations of identifying assumptions would affect the results. When the key assumptions are orthogonality between error terms and excluded instruments, we show that our measure provides a natural extension of the omitted variables bias formula for nonlinear models. We illustrate with applications to published articles in several fields of economics.

On the Informativeness of Descriptive Statistics for Structural Estimates
Abstract 2: Researchers often present treatment-control differences or other descriptive statistics alongside structural estimates that answer policy or counterfactual questions of interest. We ask to what extent confidence in the researcher’s interpretation of the former should increase a reader’s confidence in the latter. We consider a structural estimate ˆc that may depend on a vector of descriptive statistics γˆ. We define a class of misspecified models in a neighborhood of the assumed model. We then compare the bounds on the bias of ˆc due to misspecification across all models in this class with the bounds across the subset of these models in which misspecification does not affect γˆ. Our main result shows that the ratio of the lengths of these tight bounds depends only on a quantity we call the informativeness of γˆ for ˆc, which can be easily estimated even for complex models. We recommend that researchers report the estimated informativeness of descriptive statistics. We illustrate with applications to three recent papers.