Nonparametric Covariate Adjustment in Finite Samples

Part of the Lecture Notes in Economics and Mathematical Systems book series (LNE, volume 524)


In this chapter the finite-sample properties of various estimators of the covariate-adjusted mean (2.25) are investigated. Estimates of (2.25) are essential ingredients for policy evaluation under the control-for-confounding-variables and under the difference-in-difference identification approaches (discussed in Section 2.1.4). Hence precise estimation of covariate-adjusted means is of importance, particularly if average treatment effects are analyzed for smaller subpopulations.1 In addition, estimation of covariate-adjusted means is also central for deriving individually optimal treatment choices in Chapter 4.


Propensity Score Optimal Bandwidth Estimate Propensity Score Kernel Match Bandwidth Selector 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 2.
    Some simulations were also carried out with local quadratic and local cubic matching and with a local linear variant of Hall, Park, and Turlach (1998). These estimators, however, did not perform well in small samples.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  1. 1.SIAWUniversity of St. GallenSt. GallenSwitzerland

Personalised recommendations