Splitting the Difference? Causal Inference and Theories of Split-party Delegations

Abstract
We provide an introduction to the regression discontinuity design (RDD) and use the technique to evaluate models of sequential Senate elections predicting that the winning party for one Senate seat will receive fewer votes in the next election for the other seat. Using data on U.S. Senate elections from 1946 to 2004, we find strong evidence that the outcomes of the elections for the two Senate seats are independent.

This publication has 25 references indexed in Scilit: