Publication Type

Working Paper

Version

publishedVersion

Publication Date

1-2014

Abstract

Consider a nonseparable model Y=R(X,U) where Y and X are observed, while U is unobserved and conditionally independent of X. This paper provides the first nonparametric test of whether R takes the form of a transformation model, meaning that Y is monotonic in the sum of a function of X plus a function of U. Transformation models of this form are commonly assumed in economics, including, e.g., standard specifications of duration models and hedonic pricing models. Our test statistic is asymptotically normal under local alternatives and consistent against nonparametric alternatives. Monte Carlo experiments show that our test performs well in finite samples. We apply our results to test for specifications of generalized accelerated failure-time (GAFT) models of the duration of strikes and of marriages.

Keywords

additivity, control variable, endogenous variable, monotonicity, nonparametric nonseparable model, hazard model, specification test, transformation model, unobserved heterogeneity

Discipline

Econometrics

Research Areas

Econometrics

First Page

1

Last Page

35

Copyright Owner and License

Authors

Comments

Published in Journal of Econometrics https://doi.org/10.1016/j.jeconom.2014.09.008

Included in

Econometrics Commons

Share

COinS