Using principal components analysis, I derived a PC from the following state-level variables:
1. Fundamental religiosity (Z)
2. Gun owners (%)
3. Same sex households (%)
4. Starbucks:Walmart (a ratio of the number of Starbucks stores in a state relative to the number of Walmart stores)
5. Earnings gap (% more money men make versus women).
The PC explained 75% of the variance in these 5 variables. Here's scatter plots of its correlation with the percentage of self-identified liberals (r = -.91), and then conservatives (r = .90) within each state:
http://thegeneralfactor.blogspot.com...ism-by-50.html
1. Fundamental religiosity (Z)
2. Gun owners (%)
3. Same sex households (%)
4. Starbucks:Walmart (a ratio of the number of Starbucks stores in a state relative to the number of Walmart stores)
5. Earnings gap (% more money men make versus women).
The PC explained 75% of the variance in these 5 variables. Here's scatter plots of its correlation with the percentage of self-identified liberals (r = -.91), and then conservatives (r = .90) within each state:
http://thegeneralfactor.blogspot.com...ism-by-50.html
via International Skeptics Forum http://ift.tt/1CMp4zC
Aucun commentaire:
Enregistrer un commentaire