Social scientists often analyze data using models--of which there are many different kinds. One class of models -- known variously as multilevel, random effects, hierarchical, or mixed models -- are now a major tool for social science data analysis, but we're still figuring out how to make the best use of them in different kinds of studies.
I'm a frequent user of these models, and I have in some cases been able to write papers with advice for others, based on what I've learned from using them myself. For example, I've written about how to analyze what I call comparative longitudinal survey data: survey data collected in a set of societies multiple times, but where the specific people surveyed change each time.
I'm a former visiting researcher at the Research and Expertise Centre for Survey Methodology in Barcelona.
"Understanding and misunderstanding group mean centering: a commentary on Kelley et al.’s dangerous practice," 2017, Quality and Quantity (with Andrew Bell and Kelvyn Jones)
"The Random Effects in Multilevel Models: Getting Them Wrong and Getting Them Right," 2016, European Sociological Review (with Alexander Schmidt-Catran)
"Two Multilevel Modeling Techniques for Analyzing Comparative Longitudinal Survey Datasets," 2014, Political Science Research and Methods