Razib Khan

March 23, 2009

A few days ago I pointed out some minor differences in attitudes toward international intervention by ethnicity in the American South. I specifically looked in the General Social Survey at the ?USINTL? variable:

Do you think it will be best for the future of this country if we take an active part in world affairs, or if we stay out of world affairs?

I decided to expand the pool to the entire white population of the United States and slice the data by three variables, DEGREE, highest degree attained, POLVIEWS, political views, and SEI, socioeconomic index.

Lowest degree attainment to the left, highest to the right:

Extreme liberals to the left, and extreme conservatives to the right:

Finally, socioeconomic index left to right:

As you can, there is a strong trend with both education and socioeconomic index, but rather less for politics.  I used the GSS to generate a Logit regression, and noted that most of the variation is really due to degree, not socioeconomic index. In other words, the variation you see in socioeconomic index is due to underlying correlation between that variable and degree attainment. 90% of those with graduate degrees want the United States to take an active part in world affairs….