Stéphane Bonhomme


CEMFI - Calle Casado del Alisal 5 - 28014 Madrid - Spain
Phone: +34 914 290 551 - Fax: +34 914 291 056 - E-mail: bonhomme@cemfi.es


 

NEWS

I will be a professor at the University of Chicago, starting November 2013.

I was awarded a starting grant from the European Research Council, for a duration of five years, starting on January 2011.

 

BACKGROUND

I did my PhD at CREST and Université Paris I, under the supervision of Jean-Marc Robin.

You can see my CV HERE.

 

INTERESTS

Labour economics, Microeconometrics, and econometric theory.

With a special interest in latent variable modelling and panel data.

 

TEACHING

I teach Econometrics at the graduate level.

You can see some class notes at the bottom of this page.

 

CURRENT RESEARCH

 

            Working papers

 

                        Grouped Patterns  of Heterogeneity in Panel Data (with Elena Manresa)

                        Keywords: Discrete heterogeneity, panel data, fixed effects, democracy.

                                   Summary: We propose an alternative to fixed-effects estimation in linear panel data regression

                                                   that allows for group-level time-varying unobservables. We use this approach to document

                                                     the evolution of income and democracy in the last part of the XXth century.

                                                Stata code to replicate the results (regressions, trends and maps)

                                               Stata code to compute the grouped fixed-effects estimator on your data

 

 

 

 

                        The Cycle of Earnings Inequality: Evidence from Spanish Social Security Data (with Laura Hospido).

                        Keywords: Earnings Inequality, Social Security data, Unemployment, Business cycle.

                                   Summary: We use Spanish Social Security data to document the evolution of earnings

                                                   inequality since the end of the 1980's. Male inequality is strongly countercyclical,

                                                     and partly reflects the effects of the housing boom and bust on the construction

                                                   sector.

                                   A complement of the paper using tax data is:

                                   Earnings Inequality in Spain: New Evidence Using Tax Data (with Laura Hospido).

                                   Applied Economics, 45, 4212-4225.

 

 

                        Nonparametric Estimation of Finite Mixtures (with Koen Jochmans and Jean-Marc Robin)

                        Keywords: finite-mixture model, nonparametric estimation, series expansion.               

                                   Summary: We develop a practical procedure to nonparametrically estimate finite mixture

                                                    models from data on repeated measurements.       

                                   Supplement                

 

Job Characteristics and Labor Turnover: Assessing the Role of Preferences and Opportunities (with Grégory Jolivet and Edwin Leuven).

                        Keywords: labor turnover, compensating differentials, sample selection.

                                   Summary: We propose a method to estimate workers' preferences for job amenities

                                                   using data on job changes. We apply it to administrative data on Dutch primary

                                                   school teachers.                 

 

                        Quantile Selection Models (with Manuel Arellano).

                        Keywords: Quantile regression, sample selection, gender wage gap, copula.

                                   Summary: We propose a method to correct quantile regression estimates for sample

                                                   selection, and apply it to study wage and employment in the UK.                                        

 

                        Random-Effects Quantile Regression (with Manuel Arellano)

                        Keywords: Panel data, quantile regression, Expectation-Maximization.

                                   Summary: We introduce a class of linear quantile regression estimators for panel data.

                                                    Our correlated random-effects approach relies on additional layers of quantile

                                                    regressions as a flexible tool to model conditional distributions.

 

 

            Forthcoming publications

 

                        Functional Differencing.

                        Forthcoming in Econometrica (Final version: October 2011).

                  Keywords: Panel data, incidental parameters, inverse problems.

                             Summary: We propose a general method (a ``nonlinear within transformation'') to difference

                                             out the individual fixed effects in likelihood-based panel data models.

                                         Supplementary appendix

                                               Matlab codes              

 

                        Identifying Distributional Characteristics in Random Coefficients Panel Data Models (with Manuel Arellano).

                        Forthcoming in the Review of Economic Studies (Final version: June 2011).

                  Keywords: Panel data, random coefficients, multiple effects, nonparametric identification.

                             Summary: We provide identification results and construct estimators for variances, and

                                             more generally densities, of individual fixed effects in linear panel data models.

                                                Supplementary appendix

                                               Stata codes                 

 

                        Penalized Least Squares Methods for Latent Variables Models.

                        Discussion of papers prepared for the World Congress of the Econometric Society (Shanghai, 2011).

                        Keywords: Latent variables models, lasso, penalization.

                                   Summary: A discussion of papers by Susanne Schennach and Victor Chernozhukov,

                                                   where we apply a penalized least squares (``lasso'') density estimator to a

                                                   simple measurement error model.

                                               Slides

 

            Published papers

 

                        Nonlinear Panel Data Analysis (with Manuel Arellano).

                        Annual Review of Economics, 3, 395-424.                 

                        Keywords: Panel data, incidental parameters, partial identification.

                                   Summary: A survey of recent advances in panel data, including a discussion of the

                                                   computation of random-effects estimators, and partial identification. 

 

Recovering Distributions in Difference-in-Differences: A Comparison of Selective and Comprehensive Schooling (with Ulrich  Sauder).

                  Review of Economics and Statistics, 93(2), 479–494, May 2011.

                  Keywords: Selective education, difference-in-differences, treatment effects, quantiles.

                             Summary: We introduce a method to estimate distributions of potential outcomes in

                                             difference-in-differences models, and study the effect of selective secondary

                                             education in the UK.

                                         WP version.

                                               Stata codes.

 

                  Generalized Nonparametric Deconvolution with an Application to Earnings Dynamics”(with Jean-Marc Robin).

                  Review of Economic Studies, 77(2), 491-533, April 2010.

                  Keywords: Factor models, nonparametric deconvolution, earnings dynamics.

                             Summary: We propose a nonparametric estimator of factor distributions in linear factor

                                             independent factor models. We use it to estimate the distribution of earnings

                                             shocks in a simple permanent/transitory model, on PSID data.

                                         Gauss codes.

                       

                  The Pervasive  Absence of Compensating Differentials (with Grégory Jolivet).

                        Journal of Applied Econometrics, 24(5), 763-795, June 2009.

                        Keywords: Compensating wage differentials, job mobility, amenities.

                                   Summary: We build and estimate a structural job search model of wages, non-wage

                                                   amenities, and job mobility on European data. We find strong preferences

                                                   for some amenities, which are not reflected in wage/amenity correlations.

 

                  Consistent Noisy Independent Component Analysis (with Jean-Marc Robin).

                        Journal of Econometrics, 149(1), 12-25, April 2009.

                        Keywords: Factor analysis, Independent Component Analysis, higher-order moments.

                                   Summary: We propose a method to estimate linear independent factor models using

                                                   higher-order moments, and apply it to schooling data on test scores, and to

                                                   the Fama-French data on stock returns. 

                                               Supplementary appendix.

                                               Gauss codes for the ``quasi-JADE'' estimator.

 

                        Robust Priors in Nonlinear Panel Data Models (with Manuel Arellano).

                        Econometrica, 77(2), 489-536, March 2009.

                        Keywords: Panel data, integrated likelihood, bias reduction

                                   Summary: We show under which condition integrated likelihood estimators reduce first-

                                                   order bias on common parameters and average marginal effects. Our framework

                                                   covers fixed-effects, random-effects, and Bayesian approaches as special cases.   

                                               Supplementary appendix.

                                  

                        Assessing the Equalizing Force of Mobility Using Short Panels: France, 1990-2000”(with Jean-Marc Robin).

                        Review of Economic Studies, 76(1), 63-92, January 2009.

                        Keywords: Inequality, mobility, earnings dynamics, copula.

                                   Summary: We build a model of earnings dynamics that combines a flexible modelling of the

                                                   marginal distributions (inequality) with a tight parameterization of the dynamics (mobility),

                                                   and use it to compute inequality in Present Values. We estimate the model on the French

                                                   Labor Force Survey.

                                               Stata do-file.

 

            Other

 

                        Standard Errors Estimation in Mixtures of Partial Likelihood Models

                        Keywords: EM algorithm, standard errors.

                        Summary: A simple method to estimate asymptotic standard errors of sequential EM estimators,

                                       using the generalized information identity.

                       

CLASS NOTES

 

            Statistical Methods in Econometrics

 

                        1. Preliminaries

                        2. Univariate Distributions

                        3. Multivariate Distributions

                        4. Moments

                        5. Sampling

                          6. Asymptotic Theory

                        7. Estimation

                        8. Tests of Hypotheses

                        9. Regression

 

            Econometrics

 

                        1. Introduction

                        2. The Linear Model

                        3. Maximum Likelihood and asymptotic tests

                        4. Stochastic Processes

                        5. Regression with Dependent Data

                        6. Endogeneity

                        7. Generalized Method of Moments

                        8. Limited Dependent Variables

                        9. Introduction to Panel Data

                        10. Nonparametric Regression

                       

            A gentle introduction to quantile regression