The Asymptotic Variance of Semi-parametric Estimators with Generated Regressors

Arbeitspapier

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.

Object Details

• Language: Englisch

References and Relationships

• Bibliographic citation: Series: Texto para discussão ; No. 575

Classification and Topics

• Classification: Wirtschaft ; Econometrics ; Semiparametric and Nonparametric Methods: General
• Subject: Semi-parametric estimation ; generated regressors ; asymptotic variance. JEL Code: C01

Contributors, Places and Time

• Event: Geistige Schöpfung
• (who): Hahn, Jinyong ; Ridder, Geert
• Event: Veröffentlichung
• (who): Pontifícia Universidade Católica do Rio de Janeiro (PUC-Rio), Departamento de Economia
• (where): Rio de Janeiro
• (when): 2010

Further information

• Handle: http://hdl.handle.net/10419/176058
• Last update: 06.05.0014, 6:34 AM CET