The purpose of this study is to examine whether there exist significant income differences between groups of people based on their political identification. As the nation becomes more politically polarized, companies which take political stances, or even financially contribute to political candidates, risk offending and alienating a significant segment of the population. As a recent example, the Walt Disney Company decided that it would not distribute a film by Michael Moore, Farenheit 911 (despite having funded it's production), because it feared any possible backlash in an election year. Disney provided no data to support it's decision, however. It is important to know how such decisions will effect the profitability of companies, and this research is intended to offer a first step in providing quantified reasoning behind any such decisions.
The data set chosen for this project was the 1998 General Social Survey (GSS). The GSS is a large national survey conducted every 2 years since 1972 by the National Opinion Research Center at the University of Chicago. Recent results of the survey are available for analysis by scholars. The entire data set, from 1972 to 1998, is publicly available for download at a website maintained by the Inter-University Consortium for Political and Social Research (ICPSR) at the University of Michigan. It is from the 1998 dataset that this research projected selected its data.
116 responses on two variables were randomly chosen from the dataset. The variables chosen were Personal Income and Political Party Affiliation. Party affiliation is measured on a 7 point scale, with 0-2 reflecting varying levels of Democratic party affiliation, 4-6 reflecting varying levels of Republican party affiliation, and 3 reflecting Independent status. Personal Income was a two-digit number, reflecting estimated income in the thousands.
There were therefore three groups - Republican, Democrat, and Indepen...