Tomorrow at Applied Stats we will be hearing from Professor Adam Glynn (Harvard Government) who will speak on "Front-Door Difference-in-Differences Estimators: The Effects of Early In-person Voting on Turnout" (joint work with Konstantin Kashin). I've put the abstract below and included links to two different papers which are related to this project. 

As per usual, we will meet at 12noon in CGIS K354. Lunch will be served -- and it's going to be a taco bar!

See you tomorrow!

Tess

Front-Door Difference-in-Differences Estimators: The Effects of Early In-person Voting on Turnout

Abstract

In this paper, we develop front-door difference-in-differences estimators that utilize information from post-treatment variables in addition to information from pre-treatment covariates. Even when the front-door criterion does not hold, these estimators allow the identification of causal effects by utilizing assumptions that are analogous to standard difference-in-differences assumptions. We also demonstrate that causal effects can be bounded by front-door and front-door difference-in-differences estimators under relaxed assumptions. We illustrate these points with an application to the effects of early in-person voting on turnout. Despite recent claims that early voting had a negative effect on turnout in 2008, we find evidence that early in-person voting had small positive effects on turnout in Florida in 2008 and 2012.


http://scholar.harvard.edu/files/aglynn/files/fddid_0.pdf