Abstract

https://ssrn.com/abstract=2568724
 


 



Lagged Explanatory Variables and the Estimation of Causal Effects


Marc F. Bellemare


University of Minnesota - Twin Cities - Department of Applied Economics

Takaaki Masaki


Cornell University

Thomas B. Pepinsky


Cornell University - Department of Government

February 23, 2015


Abstract:     
Across the social sciences, lagged explanatory variables are a common strategy to confront challenges to causal identification using observational data. We show that “lag identification” — the use of lagged explanatory variables to solve endogeneity problems — is an illusion: lagging independent variables merely moves the channel through which endogeneity biases causal estimates, replacing a “selection on observables” assumption with an equally untestable “no dynamics among unobservables” assumption. We build our argument intuitively using directed acyclic graphs, then provide analytical results on the bias resulting from lag identification in a simple linear regression framework. We then present simulation results that characterize how, even under favorable conditions, lag identification leads to incorrect inferences. These findings have important implications for current practice among applied researchers in political science, economics, and related disciplines. We conclude by specifying the conditions under which lagged explanatory variables are appropriate for identifying causal effects.

Number of Pages in PDF File: 40

Keywords: Causal Identification, Treatment Effects, Lagged Variables

JEL Classification: C13, C15, C21


Open PDF in Browser Download This Paper

Date posted: February 24, 2015  

Suggested Citation

Bellemare, Marc F. and Masaki, Takaaki and Pepinsky, Thomas B., Lagged Explanatory Variables and the Estimation of Causal Effects (February 23, 2015). Available at SSRN: https://ssrn.com/abstract=2568724 or http://dx.doi.org/10.2139/ssrn.2568724

Contact Information

Marc F. Bellemare
University of Minnesota - Twin Cities - Department of Applied Economics ( email )
MN
United States
Takaaki Masaki
Cornell University ( email )
Ithaca, NY 14853
United States
Thomas B. Pepinsky (Contact Author)
Cornell University - Department of Government ( email )
Ithaca, NY 14853
United States
Feedback to SSRN


Paper statistics
Abstract Views: 2,027
Downloads: 420
Download Rank: 52,610