You are here
Nonparametric Estimators of Dose-response Functions
In this paper we propose three semiparametric estimators of the dose-response function based on kernel and spline techniques, respectively. Under uncounfoundedness, the generalized propensity score can be used to estimate dose-response functions (DRF) and marginal treatment effect functions. In many observational studies treatment may not be binary or categorical. In such cases, one may be interested in estimating the dose-response function in a setting with a continuous treatment. We present a set of Stata programs, which estimate the propensity score when the treatment is a continuous variable and semiparametrically estimate the dose-response function. We illustrate these programs using data coming from the survey of the Massachusetts lottery winners, collected by Imbens, Rubin and Sacerdote and described in detail in Imbens et al. (2001).
Dr. Michela Bia is currently Researcher at the Centre for Population, Poverty and Public Policy Studies (CEPS/INSTEAD) in Esch-sur-Alzette (Luxembourg). She got a PhD in Applied Statistics at the Department of Statistics “G. Parenti” of the University of Florence in 2007. Her dissertation was mainly focused on: the development of a Stata package for the estimation of the dose-response function; the evaluation of public contributions to firms. She has been researching public policies issues and currently involved in a project to develop non-parametric techniques for estimating direct and indirect causal effects. Her main expertise is the context of causal inference, program evaluation, applied statistics.
IRVAPP/Fondazione Bruno Kessler - Via Santa Croce 77 - Trento
The presentation will be in English.