Description: The average divorce rate for counties that voted for Trump is significantly higher than Clinton counties. Marriage rates, however, are virtually identical.
Observation: The average divorce rate for counties that voted for Trump is significantly higher than Clinton’s (4.05 per 1,000 people vs. 3.50 with a 96.00 confidence). Marriage rates, however, are virtually identical (1% higher for Clinton counties, though statistically insignificant). The previous “Illuminating America” entry for divorce rates1 has been updated to include the new logarithmic regression model (county-level divorce rates explain 23.1% of the 2016 election result).
1Rank of each variable based on ability to predict the 2016 election; 2Variable name; 3Percentage of counties that have data coverage; 4GOP and 5DEM variable averages; 6Confidence of difference between variable averages; 7Regression type (linear, exponential, power, or logarithmic); 8Correlation between variable and Trump vote; 9R-squared value.
Methods and data: County-level divorce rates are taken from the National Center for Family & Marriage Research with the Center for Family and Demographic Research2. County-level 2016 election results were compiled by Charted Territory by visiting each state’s Secretary of State web page. The data were compiled and visualized using Microsoft Excel3.