Discussion Paper Series, University of Heidelberg, Department of Economics 417
This article shows how to construct a likelihood for a general class of censoring problems. This likelihood is proven to be valid, i.e. its maximiser is consistent and the respective root-n estimator is asymptotically efficient and normally distributed under regularity conditions. The method generalises ordinary maximum likelihood estimation as well as several standard estimators for censoring problems (e.g. tobit type I - tobit type V).
Censored variables Limited dependent variables Multivariate methods Random censoring Likelihood