Researchers often report estimates and standard errors for the object of interest (such as a treatment effect) based on a single specification of a statistical model. We propose a systematic approach to assessing sensitivity to specification. We construct estimates of the object of interest for each of a large set of models. Our proposed robustness measure is the standard deviation of the point estimates over the set of models. Each member of the set is generated by splitting the sample into two subsamples based on covariate values, constructing separate parameter estimates for each subsample, and then combining the results.
