Lessons from Specification Tests for a Labour Supply Model

This paper investigates the properties of Box-Cox specifications for the labour supply of married women in France, estimated in four stages involving two dichotomous models, a regression with selectivity correction, and the calculation of sample means. Previous estimates implied wage elasticities high enough to be seriously questioned. We re-estimate the model with a more flexible stochastic specification and allow for some variation in the preference parameters across individuals. Furthermove, we account for a certain kind of heteroscedasticity. We submit all steps of the estimation to specification tests using among others LM tests against heteroscedasticity and misspecification of the distribution, information matrix tests, Andrews' X?-tests, Vuong's LR-test for non-nested alternatives. Although we do find somewhat lower elasticities the detected heteroscedasticity or parameter stability problems appear to be serious enough to caution against use of these models for policy simulation.