Event

Lunchseminar in Economics: Irregular Identification of Structural Models with Nonparametric Unobserved Heterogeneity

  • Conférencier  Juan Carlos Escanciano, Universidad Carlos III de Madrid, ES

  • Lieu

    ONLINE ACCESS

    LU

  • Thème(s)
    Sciences économiques & gestion

One of the most important empirical findings in microeconometrics is the pervasiveness of heterogeneity in economic behaviour (cf. Heckman 2001). This paper shows that distribution functions and quantiles of the nonparametric unobserved heterogeneity have an infinite efficiency bound in many structural economic models of interest. The paper presents a novel and relatively simple check of this fact. The usefulness of the theory is demonstrated by showing irregular identification in several relevant examples in economics, including, among others, the proportion of individuals with severe long term unemployment duration, Average Marginal Effects (AME) in a correlated random coefficient model, and the distribution and quantiles of random coefficients in linear, binary and the semi-parametric Mixed Logit models.

 isResearch Chair in Economics and Full Professor at Universidad Carlos III de Madrid. He obtained his P.hD in Economics at Universidad Carlos III de Madrid in 2004.  He obtained an Assistant Professor position at Universidad de Navarra (2004-2006), Full Professor (with tenure) at Indiana University (2006-2018), and Visiting positions at Yale University, Cornell, Rochester and MIT. His research and teaching focus on Econometric Theory, including identification, estimation and specification testing, as well as empirical work in Financial Econometrics and Risk Management.

Juan Carlos is Fellow of Journal of Econometrics. He has published papers in several leading international journals, including Journal of American Statistical Association, Journal of Econometrics, Econometric Theory, Quantitative Economics, Management Science, and The Annals of Statistics. He is Associate Editor of  Series, Econometric Theory, Econometric Reviews, Journal of Business and Economic Statistics, and Co-Editor senior in Advances in Econometrics.

Registration

– Free seminar

– Registration to dem@uni.lu (please specify full name and institution)