Who's Fixed?

Sep 13, 2018 - 3 minutes
When comparing a multilevel model to a fixed-level model, it’s important to consider how things are parameterized. For instance, let’s say you’re conducting comparisons between a no-pooling model and a partial pooling variance components model. In this case, we have: $$ y= \Delta u + \epsilon$$ as the specification, where $\Delta$ is the dummy variable matrix, $y$ is the outcome of interest, and $\epsilon$ is the usual homoeskedastic error term for the responses. Read more ...

The Geometer's Angle

Jul 30, 2018 - 9 minutes
The Geometer’s Angle What John O’Loughlin talks about in his recent presidential address in Political Geography strikes me as substantially similar to many of the things I’ve read from him on the field. Indeed, it reminds me of the same track I got from him as a PhD applicant seeking to work in quantitative political geography. I’ll never forget; right at the time of (what I thought and still feel is) great ground-breaking work in political science focusing directly on the new understandings possible from aggregate electoral data [1,2,3] he suggested that electoral analysis needed to go beyond this. Read more ...

Using lookahead testing

Jul 24, 2018 - 6 minutes
To help subpackages that depend on libpysal, the API will change shortly to be in line with our desired migrating.pysal.org API. If you test your package against the pypi version of libpysal (which you get using pip install libpysal), you already know that your changes don’t break with respect to what exists. However, if you’d like to give yourself some lead time to detect if there are breaking changes in the development version of libpysal on github, feel free to follow these directions on how to set up optional tests on travis. Read more ...