Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/259870 
Year of Publication: 
2003
Series/Report no.: 
Working Paper No. 2003:4
Publisher: 
Lund University, School of Economics and Management, Department of Economics, Lund
Abstract: 
In this paper we develop a simple maximum likelihood estimator for probit models where the regressors have measurement error. We first assume precise information about the reliability ratios (or, equivalently, the proxy correlations) of the regressors. We then show how reasonable bounds for the parameter estimates can be obtained when only imprecise information is available. The analysis is also extended to situations where the measurement error has non-zero mean and is correlated with the true values of the regressors. An extensive simulation study shows that the estimator works very well, even in quite small samples. Finally the method is applied to data explaining sick leave in Sweden.
Subjects: 
Measurement error
errors-in-variables
probit
binary choice
bounds
JEL: 
C25
C29
Additional Information: 
Gauss program available.
Document Type: 
Working Paper

Files in This Item:
File
Size





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.