Getting the Politics Right in Election Research - Christopher Achen, December 9|10, 2021
Posted on Wednesday, Oct 13, 2021
The biggest challenge in empirical work is to get our statistical models to correctly represent the politics of what we are studying. For example, Donald Trump raised voter turnout. So did Franklin Roosevelt and Adolf Hitler. Strong preferences motivate voters to go to the polls. Yet studies of elections nearly always analyze vote choices and turnout separately, missing the politics that mobilizes voters. Researchers have long understood the theoretical limitation of doing so, but issues of parameter identification, computing power, unavailability of survey weighting, and complexity of interpretation have kept most researchers from using the appropriate statistical tools. However, these problems have now largely been overcome, which this paper illustrates with studies of the 2016 U.S. presidential election and the 2017 South Korean presidential election. I conclude with some thoughts about the appropriate future direction for political methodology.