Endogeneity in Probit Response Models
Preprint
- 29 May 2008
- preprint
- Published by Elsevier BV in SSRN Electronic Journal
Abstract
In this paper, we look at conventional methods for removing endogeneity bias in regression models, including the linear model and the probit model. The usual Heckman two-step procedure should not be used in the probit model: from a theoretical perspective, this procedure is unsatisfactory, and likelihood methods are superior. However, serious numerical problems occur when standard software packages try to maximize the biprobit likelihood function, even if the number of covariates is small. The log likelihood surface may be nearly flat, or may have saddle points with one small positive eigenvalue and several large negative eigenvalues. We draw conclusions for statistical practice. Finally, we describe the conditions under which parameters in the model are identifiable; these results appear to be new.Keywords
This publication has 16 references indexed in Scilit:
- Modeling Selection EffectsPublished by SAGE Publications ,2011
- How Can the Score Test Be Inconsistent?The American Statistician, 2007
- Is the Magic Still There? The Use of the Heckman Two-Step Correction for Selection Bias in CriminologyJournal of Quantitative Criminology, 2007
- Estimating probit models with self-selected treatmentsStatistics in Medicine, 2005
- Causal Inference and the Heckman ModelJournal of Educational and Behavioral Statistics, 2004
- Inference for Non-random SamplesJournal of the Royal Statistical Society Series B: Statistical Methodology, 1997
- A Structural Probit Model with Latent VariablesJournal of the American Statistical Association, 1979
- Sample Selection Bias as a Specification ErrorEconometrica, 1979
- Dummy Endogenous Variables in a Simultaneous Equation SystemEconometrica, 1978
- Table of the Ratio: Area to Bounding Ordinate, for Any Portion of Normal CurveBiometrika, 1926