Irregular Identification of Structural Models with Nonparametric Unobserved Heterogeneity

Mad-Stat./Econometrics and Empirical Economics joint seminar

Juan Carlos Escanciano (Universidad Carlos III de Madrid)

September 17, 2020, 11:00–12:15


Room Zoom

MAD-Stat. Seminar


One of the most important empirical findings in microeconometrics is the pervasive ness 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, bounds on average equivalent variation under endogeneity, and the distribution and quantiles of random coe¢ cients in linear, binary and the semiparametric Mixed Logit models. In particular, it is shown that the commonly used monotonicity assumption is necessary for regular identification of the AME in a model with heterogenous effects.