Posterior average effects

Arbeitspapier

Economists are often interested in estimating averages with respect to distributions of unobservables. Examples are moments of individual fixed-effects, average effects in discrete choice models, or counterfactual simulations in structural models. For such quantities, we propose and study "posterior average effects", where the average is computed conditional on the sample, in the spirit of empirical Bayes and shrinkage methods. While the usefulness of shrinkage for prediction is well-understood, a justification of posterior conditioning to estimate population averages is currently lacking. We establish two robustness properties of posterior average effects under misspecification of the assumed distribution of unobservables: they are optimal in terms of local worst-case bias, and their global bias is at most twice the minimum worst-case bias within a large class of estimators. We establish related robustness results for posterior predictors. In addition, we suggest a simple measure of the information contained in the posterior conditioning. Lastly, we present two empirical illustrations, to estimate the distributions of neighborhood effects in the US, and of permanent and transitory components in a model of income dynamics.

Show object

• Language: Englisch

References and Relationships

• Bibliographic citation: Series: cemmap working paper ; No. CWP43/19

Classification and Topics

• Classification: Wirtschaft ; Estimation: General ; Single Equation Models; Single Variables: Panel Data Models; Spatio-temporal Models
• Subject: model misspeci cation ; robustness ; sensitivity analysis ; empirical Bayes ; posterior conditioning ; latent variables

Contributors, Places and Time

• Event: Geistige Schöpfung
• (who): Bonhomme, Stéphane ; Weidner, Martin
• Event: Veröffentlichung
• (who): Centre for Microdata Methods and Practice (cemmap)
• (where): London
• (when): 2019

Further information

• DOI: doi:10.1920/wp.cem.2019.4319
• Handle: http://hdl.handle.net/10419/211136