Replicating Experimental Impact Estimates with Nonexperimental Methods in the Context of Control Crossover

Working Paper 21
Publisher: Cambridge, MA: Mathematica Policy Research
Oct 30, 2013
Brian Gill, Joshua Furgeson, Hanley S. Chiang, Bing-Ru Teh, Joshua Haimson, and Natalya Verbitsky-Savitz
Ideally, nonexperimental methods that aim to replicate the results of rigorous randomized experiments focus on the intent to treat (ITT) experimental impact estimate, the most causally rigorous measure. This working paper develops a new replication approach that facilitates testing nonexperimental methods against rigorous experimental ITT impact estimates when the experiment includes substantial control crossover.