TY - JOUR
T1 - Variance estimation for average treatment effects estimated by g-computation
AU - Hansen, Stefan Nygaard
AU - Overgaard, Morten
PY - 2024/4/6
Y1 - 2024/4/6
N2 - The average treatment effect is used to evaluate effects of interventions in a population. Under certain causal assumptions, such an effect may be estimated from observational data using the g-computation technique. The asymptotic properties of this estimator appears not to be well-known and hence bootstrapping has become the preferred method for estimating its variance. Bootstrapping is, however, not an optimal choice for multiple reasons; it is a slow procedure and, if based on too few bootstrap samples, results in a highly variable estimator of the variance. In this paper, we consider estimators of potential outcome means and average treatment effects using g-computation. We consider these parameters for the entire population but also in subgroups, for example, the average treatment effect among the treated. We derive their asymptotic distributions in a general framework. An estimator of the asymptotic variance is proposed and shown to be consistent when g-computation is used in conjunction with the M-estimation technique. The proposed estimator is shown to be superior to the bootstrap technique in a simulation study. Robustness against model misspecification is also demonstrated by means of simulations.
AB - The average treatment effect is used to evaluate effects of interventions in a population. Under certain causal assumptions, such an effect may be estimated from observational data using the g-computation technique. The asymptotic properties of this estimator appears not to be well-known and hence bootstrapping has become the preferred method for estimating its variance. Bootstrapping is, however, not an optimal choice for multiple reasons; it is a slow procedure and, if based on too few bootstrap samples, results in a highly variable estimator of the variance. In this paper, we consider estimators of potential outcome means and average treatment effects using g-computation. We consider these parameters for the entire population but also in subgroups, for example, the average treatment effect among the treated. We derive their asymptotic distributions in a general framework. An estimator of the asymptotic variance is proposed and shown to be consistent when g-computation is used in conjunction with the M-estimation technique. The proposed estimator is shown to be superior to the bootstrap technique in a simulation study. Robustness against model misspecification is also demonstrated by means of simulations.
KW - Average treatment effect
KW - Causal inference
KW - G-computation
KW - Model misspecification
KW - Variance estimation
UR - http://www.scopus.com/inward/record.url?scp=85189481313&partnerID=8YFLogxK
U2 - 10.1007/s00184-024-00962-4
DO - 10.1007/s00184-024-00962-4
M3 - Journal article
SN - 0026-1335
JO - Metrika
JF - Metrika
ER -