Estimation in Binary Choice Models with Measurement Errors
(2003) In Working Papers, Department of Economics, Lund University- 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
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/1386380
- author
- Jochumzen, Peter LU
- organization
- publishing date
- 2003
- type
- Working paper/Preprint
- publication status
- unpublished
- subject
- keywords
- Measurement error, errors-in-variables, probit, binary choice, bounds
- in
- Working Papers, Department of Economics, Lund University
- issue
- 4
- publisher
- Department of Economics, Lund University
- language
- English
- LU publication?
- yes
- id
- 3c11ab8c-bdcb-430e-beb2-c3efaccadc0e (old id 1386380)
- alternative location
- http://swopec.hhs.se/lunewp/abs/lunewp2003_004.htm
- date added to LUP
- 2016-04-04 10:51:26
- date last changed
- 2018-11-21 21:01:12
@misc{3c11ab8c-bdcb-430e-beb2-c3efaccadc0e, 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}}, author = {{Jochumzen, Peter}}, keywords = {{Measurement error; errors-in-variables; probit; binary choice; bounds}}, language = {{eng}}, note = {{Working Paper}}, number = {{4}}, publisher = {{Department of Economics, Lund University}}, series = {{Working Papers, Department of Economics, Lund University}}, title = {{Estimation in Binary Choice Models with Measurement Errors}}, url = {{https://lup.lub.lu.se/search/files/5637346/2060140}}, year = {{2003}}, }