The 2008 Election: A Preregistered Replication Analysis

ABSTRACT We present an increasingly stringent set of replications, a multilevel regression and poststratification analysis of polls from the 2008 U.S. presidential election campaign, focusing on a set of plots showing the estimated Republican vote share for whites and for all voters, as a function of income level in each of the states.  We start with a nearly exact duplication that uses the posted code and changes only the model-fitting algorithm; we then replicate using already-analyzed data from 2004; and finally we set up preregistered replications using two surveys from 2008 that we had not previously looked at. We have already learned from our preliminary, nonpreregistered replication, which has revealed a potential problem with the earlier published analysis; it appears that our model may not sufficiently account for nonsampling error, and that some of the patterns presented in that earlier article may simply reflect noise.  In addition to the substantive interest in validating earlier findings about demographics, geography, and voting, the present project serves as a demonstration of preregistration in a setting where the subject matter is historical (and thus the replication data exist before the preregistration plan is written) and where the analysis is exploratory (and thus a replication cannot be simply deemed successful or unsuccessful based on the statistical significance of some particular comparison).  Our replication analysis produced graphs that showed the same general pattern of income and voting as we had found in our earlier published work, but with some differences in particular states that we cannot easily explain and which seem too large to be explained by sampling variation. This process thus demonstrates how replication can raise concerns about an earlier published result.