Thanks to Ron Unz for his thoughtful (and prompt!) response to my critique. He said a handful of things that I would like to explore further, perhaps in a post at the Enterprise Blog. Here I want to correct a small but important error made originally by Ed Rubenstein and repeated by Unz in his response to me. In an otherwise insightful article, Rubenstein said:
"The Census lumps the prison population into a larger category -- people living in 'Group quarters'. But this category includes people in college dorms, nursing homes, and military bases."
This is not true. The Census has a subcategory within "group quarters" called institutionalization. Institutionalization includes only people in correctional facilities, mental hospitals, and nursing homes. It does not include anyone in college dorms or military bases, which are both part of a different subcategory. The point is important because I used institutionalization as a proxy for incarceration in my response to Unz, and he criticized my analysis by citing Rubenstein's inaccurate claim.
Of course, institutionalization is not a perfect measure of incarceration, but it's significantly better than as portrayed by Rubenstein and Unz. As I wrote in a footnote to my article:
"Given the pre-retirement age range I use, nursing homes should not be skewing the data. And if Hispanics disproportionately end up in mental hospitals, then frankly that's something we would want to know about anyway."