Partial Identification of Population Average and Quantile Treatment Effects in Observational Data Under Sample Selection

Christelis, D. and Messina, J. (2019) Partial Identification of Population Average and Quantile Treatment Effects in Observational Data Under Sample Selection. Working Paper. Social Science Research Network. (doi: 10.2139/ssrn.3304374).

Full text not currently available from Enlighten.

Publisher's URL: https://doi.org/10.2139/ssrn.3304374

Abstract

We partially identify population treatment effects in observational data under sample selection, without the benefit of random treatment assignment. We provide bounds both for the average and the quantile population treatment effects, combining assumptions for the selected and the non-selected subsamples. We show how different assumptions help narrow identification regions, and illustrate our methods by partially identifying the effect of maternal education on the 2015 PISA math test scores in Brazil. We find that while sample selection increases considerably the uncertainty around the effect of maternal education, it is still possible to calculate informative identification regions.

Item Type:Research Reports or Papers (Working Paper)
Keywords:Sample selection, population treatment effects, partial identification, bounds, observational data, PISA, Brazil.
Status:Published
Glasgow Author(s) Enlighten ID:Christelis, Professor Dimitris
Authors: Christelis, D., and Messina, J.
Subjects:H Social Sciences > HA Statistics
H Social Sciences > HB Economic Theory
College/School:College of Social Sciences > Adam Smith Business School > Economics
Publisher:Social Science Research Network

University Staff: Request a correction | Enlighten Editors: Update this record