Models of Truncation, Sample Selection, and Limited Dependent Variables: Suggestions for a Common Language

The aim of this paper is two-fold: (a) to establish a ‘map’ for describing the wide class of Limited Dependent Variables (LDV) univariate and multivariate models in the econometric literature and (b) to localize typical models in this tradition within the structure, extending typologies of Heckman (1976) and Amemiya (1984). The classification system, or language, proposed, is given at different level of detail. Its scope is (1) that the latent variables can have any parametric distribution, (2) that a set of observation rules which include the observed, censored, missing status, is imposed, (3) that it should be possible to write a model combining (1) and (2) by means of a computer algorithm, also potentially applicable for generating samples and (4) that the models belonging to the system should have names to facilitate communication among researchers. The likelihood functions corresponding to the models’ observed endogenous variables are discussed, but the paper is not concerned with describing the application of these functions for inference.