EconStor >
Institute for Fiscal Studies (IFS), London >
cemmap working papers, Centre for Microdata Methods and Practice, Institute for Fiscal Studies (IFS) >

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10419/64684
  
Title:The asymptotic variance of semi-parametric estimators with generated regressors PDF Logo
Authors:Hahn, Jinyong
Ridder, Geert
Issue Date:2010
Series/Report no.:cemmap working paper CWP23/10
Abstract:We study the asymptotic distribution of three-step estimators of a finite dimensional parameter vector where the second step consists of one or more nonparametric regressions on a regressor that is estimated in the first step. The first step estimator is either parametric or non-parametric. Using Newey's (1994) path-derivative method we derive the contribution of the first step estimator to the influence function. In this derivation it is important to account for the dual role that the first step estimator plays in the second step non-parametric regression, i.e., that of conditioning variable and that of argument. We consider three examples in more detail: the partial linear regression model estimator with a generated regressor, the Heckman, Ichimura and Todd (1998) estimator of the Average Treatment Effect and a semi-parametric control variable estimator.
Subjects:semi-parametric estimation
generated regressors
asymptotic variance
JEL:C01
C14
Persistent Identifier of the first edition:doi:10.1920/wp.cem.2010.2310
Document Type:Working Paper
Appears in Collections:cemmap working papers, Centre for Microdata Methods and Practice, Institute for Fiscal Studies (IFS)

Files in This Item:
File Description SizeFormat
636320251.pdf314.97 kBAdobe PDF
No. of Downloads: Counter Stats
Download bibliographical data as: BibTeX
Share on:http://hdl.handle.net/10419/64684

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