Classification Trees for Heterogeneous Moment-Based Models

54 Pages Posted: 27 Dec 2016 Last revised: 13 Oct 2022

See all articles by Sam Asher

Sam Asher

World Bank Development Research Group (DECRG)

Denis Nekipelov

University of Virginia

Paul Novosad

Dartmouth College

Stephen Ryan

Washington University in St. Louis - John M. Olin Business School

Date Written: December 2016

Abstract

A basic problem in applied settings is that different parameters may apply to the same model in different populations. We address this problem by proposing a method using moment trees; leveraging the basic intuition of a classification tree, our method partitions the covariate space into disjoint subsets and fits a set of moments within each subspace. We prove the consistency of this estimator and show standard rates of convergence apply post-model selection. Monte Carlo evidence demonstrates the excellent small sample performance and faster-than-parametric convergence rates of the model selection step in two common empirical contexts. Finally, we showcase the usefulness of our approach by estimating heterogeneous treatment effects in a regression discontinuity design in a development setting.

Suggested Citation

Asher, Sam and Nekipelov, Denis and Novosad, Paul and Ryan, Stephen, Classification Trees for Heterogeneous Moment-Based Models (December 2016). NBER Working Paper No. w22976, Available at SSRN: https://ssrn.com/abstract=2890080

Sam Asher (Contact Author)

World Bank Development Research Group (DECRG) ( email )

1818 H. Street, N.W.
MSN3-311
Washington, DC 20433
United States

HOME PAGE: http://samuelasher.com

Denis Nekipelov

University of Virginia ( email )

1400 University Ave
Charlottesville, VA 22903
United States

Paul Novosad

Dartmouth College ( email )

Department of Sociology
Hanover, NH 03755
United States

Stephen Ryan

Washington University in St. Louis - John M. Olin Business School ( email )

One Brookings Drive
Campus Box 1133
St. Louis, MO 63130-4899
United States

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
25
Abstract Views
280
PlumX Metrics