The Political Scientist

If you had told me a year or two ago that I would one day learn how to estimate a structural topic model (STM) -- an unsupervised machine learning based form of text analysis that incorporates “metadata” (i.e., a matrix of covariates) in the estimation of a generalized linear model of topical prevalence and content -- I would have either laughed until I cried or stared blankly at you wondering if either you or I had just had a stroke because I didn't understand a word of the gibberish that just came out of your mouth. And yet, here I am, taking my first steps into the wild world of text analysis. Unlike other, more traditional quantitative methods, topic models allow researchers to conduct statistical analysis on textual data -- open-ended survey questions, newspaper articles, blogs, transcripts, etc.  -- where "topics" (i.e., sets of highly associated words) are identified, not by a person, but by an algorithm, allowing users to conduct statistical a...

As promised, I've completed further analysis of the impact of various factors on median household income at the metropolitan area level, the results of which are displayed and discussed below. Rather than focus on median household income in general, I've gone a step further with this analysis by looking at variation in median household income by income tier -- e.g., lower income, middle income, and upper income tiers. The results are interesting (at least I think so...), and they arguably have significance for public policy. Also, if you don't care for all the glorious (ok...boring) details in the following analysis, just scroll on down to the conclusion. In my previous post I alluded to what I viewed as a misguided hyper-focus on security, crime, and undocumented immigration in this current presidential election season (most notably because of the rhetoric of the Republican nominee) that has distracted from other important social and economic issues. Now, I certainly thi...

While this election season has a particular candidate caricaturing himself as a "law and order" candidate, violence and crime are far from what ails this country. Most reports show that crime is down across the U.S., and while police deaths (and really all deaths) are tragedies in their own right, this issue has been largely exaggerated. These are certainly important problems, but many of the issues that impact the majority of Americans are economic and social in nature. Regarding the economic problems, household income is a particularly important issue. So, in continuation with the theme of my last post, I'd like to present some of my findings from an analysis I did of the factors associated with variation in median household income in 229 U.S. metropolitan areas. I'll try to give the least technical presentation that I can of the data as I discuss my findings. ***A quick disclaimer on causation: Statistical models are amazing tools, but it's often the respo...