The Empirical Trap of Sign Reversals with Equality Restrictions
| dc.contributor.author | Haynes, Stephen E., 1945- | |
| dc.date.accessioned | 2005-09-02T23:33:12Z | |
| dc.date.available | 2005-09-02T23:33:12Z | |
| dc.date.issued | 2005-01-15 | |
| dc.description | 11 p. | en |
| dc.description.abstract | This note explores the insidious empirical trap posed by two common equality restrictions in regression analysis. The trap is that restricted coefficients can lie outside the interval of unrestricted coefficients and even reverse sign when negatively correlated regressors are added to one another or when positively correlated regressors are subtracted from one another. | en |
| dc.format.extent | 170659 bytes | |
| dc.format.mimetype | application/pdf | |
| dc.identifier.uri | https://hdl.handle.net/1794/1315 | |
| dc.language.iso | en_US | en |
| dc.publisher | University of Oregon, Dept of Economics | en |
| dc.relation.ispartofseries | University of Oregon Economics Department Working Papers ; 2005-08 | en |
| dc.subject | Equality restrictions | en |
| dc.subject | Sign reversals | en |
| dc.subject | Invalid restrictions | en |
| dc.title | The Empirical Trap of Sign Reversals with Equality Restrictions | en |
| dc.type | Working Paper | en |