I’m just back from the Society for Research on Educational Effectiveness meetings, where I presented work on small-sample corrections for cluster-robust variance estimators in two-stage least squares models, which I’ve implemented in the clubSandwich R package.
In settings with independent observations, sample size is one way to quickly characterize the precision of an estimate. But what if your estimate is based on weighted data, where each observation doesn’t necessarily contribute to equally to the estimate?
Regression discontinuity designs (RDDs) are now a widely used tool for program evaluation in economics and many other fields. RDDs occur in situations where some treatment/program of interest is assigned on the basis of a numerical score (called the running variable), all units scoring above a certain threshold receiving treatment and all units scoring at or below the threshold having treatment withheld (or vice versa, with treatment assigned to units scoring below the threshold).
NOTE (2019-09-24): This post pertains to version 0.56 of the rdd package. The problems described in this post have been corrected in version 0.57 of the package, which was posted to CRAN on 2016-03-14.
I’ve recently been working with my colleague Beth Tipton on methods for cluster-robust variance estimation in the context of some common econometric models, focusing in particular on fixed effects models for panel data—or what statisticians would call “longitudinal data” or “repeated measures.