The authors gratefully acknowledge the useful comments of Adrian Pagan, an anonymous referee and the editor. Any remaining errors are ours.
Correcting Standard Errors in Two-stage Estimation Procedures with Generated Regressands†
Article first published online: 20 MAY 2005
Oxford Bulletin of Economics and Statistics
Volume 67, Issue 3, pages 421–433, June 2005
How to Cite
Dumont, M., Rayp, G., Thas, O. and Willemé, P. (2005), Correcting Standard Errors in Two-stage Estimation Procedures with Generated Regressands. Oxford Bulletin of Economics and Statistics, 67: 421–433. doi: 10.1111/j.1468-0084.2005.00126.x
- Issue published online: 20 MAY 2005
- Article first published online: 20 MAY 2005
- Final Manuscript Received: October 2004
Feenstra and Hanson [NBER Working Paper No. 6052 (1997)] propose a procedure to correct the standard errors in a two-stage regression with generated dependent variables. Their method has subsequently been used in two-stage mandated wage models [Feenstra and Hanson, Quarterly Journal of Economics (1999) Vol. 114, pp. 907–940; Haskel and Slaughter, The Economic Journal (2001) Vol. 111, pp. 163–187; Review of International Economics (2003) Vol. 11, pp. 630–650] and for the estimation of the sector bias of skill-biased technological change [Haskel and Slaughter, European Economic Review (2002) Vol. 46, pp. 1757–1783]. Unfortunately, the proposed correction is negatively biased (sometimes even resulting in negative estimated variances) and therefore leads to overestimation of the inferred significance. We present an unbiased correction procedure and apply it to the models reported by Feenstra and Hanson (1999) and Haskel and Slaughter (2002).