This is the sixth installment in my series on Trump’s vote in PA and County Health Rankings (CHR). This post focuses on Census participation at the county level. It is defined as “Percentage of all households that self-responded to the 2020 census (by internet, paper questionnaire or telephone).” This measures civic engagement. Census participation and Trump’s vote at the county level in PA are considered in this post.
The model states that for every one percent increase in Census participation, there is a predicted 0.155% increase in Trump’s vote. This variable has the weakest association with Trump’s vote of all the seven variables in the model. A different pattern emerges when we look at the two variables outside of the model.
The graph above shows the relationship between the two variables. There was a nonlinear negative cubic relationship accounting for 18.4% of the variance. As usual Philadelphia county is an outlier with 55% census participation and 20% of the vote for Trump.
In the multiple regression model, there was a positive association. Clearly other factors not accounted for in the graph are influencing this relationship. The multiple regression model adjusts for the influences of the other variables (Flu vaccination, access to exercise, housing cost burden, and the percent with some college). It accounts for 92.9% of the variability. Multicollinearity is not an issue in this model.
Allegheny Independent Media is affiliated with Nonprofit Partners. It is a subsidiary of the Community Foundation for the Alleghenies. Through the site you can donate to the website. It is essential to allow us to provide coverage to the critical issues facing the Alleghenies. You may donate to our site here.