Handbook of Econometrics
This chapter has surveyed the current state of econometric models and methods for the analysis of qualitative dependent variables. It discusses that the models of economic optimization that are presumed to govern conventional continuous decisions are equally appropriate for the analysis of discrete response. While the intensive marginal conditions associated with many continuous decisions are not applicable, the characterization of economic agents as optimizers implies conditions at the extensive margin and substantive restrictions on functional form. Unless the tenets of the behavioral theory are themselves under test, it is good econometric practice to impose these restrictions as maintained hypotheses in the construction of discrete response models. As a formulation in terms of latent variable models makes clear, qualitative response models share many of the features of conventional econometric systems. Thus the problems and methods arising in the main stream of econometric analysis mostly transfer directly to discrete response. Divergences from the properties of the standard linear model arise from nonlinearity rather than from discreteness of the dependent variable. Thus, most developments in the analysis of nonlinear econometric systems apply to qualitative response models. In summary, methods for the analysis of qualitative dependent variables are part of the continuing development of econometric technique to match the real characteristics of economic behavior and data.