dc.contributor.author | Andersson, Jonas | |
dc.contributor.author | Møen, Jarle | |
dc.date.accessioned | 2009-10-19T11:39:29Z | |
dc.date.available | 2009-10-19T11:39:29Z | |
dc.date.issued | 2009-09 | |
dc.identifier.issn | 1500-4066 | |
dc.identifier.uri | http://hdl.handle.net/11250/163981 | |
dc.description.abstract | Two measures of an error-ridden explanatory variable make it possible to solve
the classical errors-in-variable problem by using one measure as an instrument for
the other. It is well known that a second IV estimate can be obtained by reversing
the roles of the two measures. We explore a simple estimator that is the linear
combination of these two estimates, that minimizes the asymptotic mean squared
error. In a Monte Carlo study we show that the gain in precision is signifcant
compared to using only one of the original IV estimates. The proposed estimator
also compares well with full information maximum likelihood under normality. | en |
dc.language.iso | eng | en |
dc.publisher | Norwegian School of Economics and Business Administration. Department of Finance and Management Science | en |
dc.relation.ispartofseries | Discussion paper | en |
dc.relation.ispartofseries | 2009:10 | en |
dc.subject | measurement errors | en |
dc.subject | classical errors-in-variables | en |
dc.subject | multiple indicator method | en |
dc.subject | instrumental variable techniques | en |
dc.title | A simple improvement of the IV estimator for the classical errors-in-variables problem | en |
dc.type | Working paper | en |
dc.subject.nsi | VDP::Samfunnsvitenskap: 200::Økonomi: 210::Bedriftsøkonomi: 213 | en |