This is, basically, the third post in a series of posts about estimating and, now, exploring achievement gap variation between schools. The first post described the method, while the second applied the method to estimate achievement gaps for all schools reporting data on students coded as Hispanic and White in California. That post included some preliminary explorations of the data, but this post will take that further by looking at the variance geographically.

In the last post I talked about one method to estimate distributional differences from ordinal data, such as those reported by statewide accountability systems. In this post, we’ll put this method to work for the state of California. I’ll show how we can estimate school-level Hispanic/White achievement gaps for every school in the state that reports data on both groups. In California, this means the school must have at least 30 students in each group, for the corresponding grade.

Intro One of the neatest things I’ve learned about in the last few years is how to estimate effect sizes from coarsened data. The original article discussed using the method with publicly available data reported by statewide education agencies, and that’s the approach I’ll use here too. But more generally, the method could be applied in any situation in which a continuous distribution is reported out in ordinal bins. Background In case you’re unfamiliar, states administer tests to students at the end of the year in each of Grades 3-8, and once in high school, for all students in their state in English/Language Arts and Mathematics.

This week I’m at the Seattle branch of the Summer Institute on Computational Social Science. Today, we discussed digital trace data and spent some time thinking about different sources of digital trace data. One of the easiest sources is twitter, and thanks to Mike Kearney, it’s easily accessible in R via the {rtweet} package! I joined a group addressing a topic I find myself dwelling on throughout the day - the immigration crisis at the border.

I gave a lightning talk (slides here) this past weekend at the second annual Cascadia R Conference that was focused on creating and contributing new themes to the {xaringan} package, which is essentially a really well thought out and well-organized R Markdown wrapper around the remark.js package for producing beautiful HTML slides. At the end of that talk, I announced the work-in-progress version of my new R package, {slidex}, for converting Microsoft PowerPoint slides to R Markdown, and specifically {xaringan}, with a single function.