Working Paper: NBER ID: w24117
Authors: Pierre Nguimkeu; Augustine Denteh; Rusty Tchernis
Abstract: Participation in social programs is often misreported in survey data, complicating the estimation of the effects of those programs. In this paper, we propose a model to estimate treatment effects under endogenous participation and endogenous misreporting. We show that failure to account for endogenous misreporting can result in the estimate of the treatment effect having an opposite sign from the true effect. We present an expression for the asymptotic bias of both OLS and IV estimators and discuss the conditions under which sign reversal may occur. We provide a method for eliminating this bias when researchers have access to information related to both participation and misreporting. We establish the consistency and asymptotic normality of our estimator and assess its small sample performance through Monte Carlo simulations. An empirical example is given to illustrate the proposed method.
Keywords: treatment effects; endogenous misreporting; social programs
JEL Codes: C35; C51; I28
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| endogenous misreporting (D91) | treatment effect estimates (C22) |
| true participation status (J22) | observed participation status (C90) |
| misreporting (C59) | observable covariates (C29) |
| correlations among error terms (C21) | asymptotic bias of OLS estimator (C51) |
| two-step estimator (C51) | consistent estimates of true treatment effect (C22) |
| true treatment effect (C22) | treatment effect estimates (C22) |