Levi Wolf | On Space and Place in Predictive Models
03 February 2021, 5:00 pm–6:00 pm
Dr Max Nathan
Models are representations of reality. Generally, we all want models that are detailed "enough," but that are easy to interpret and estimate. Sometimes, we get lucky: multilevel models provide incredibly powerful specifications that are easy to understand and easier to fit thanks to some of their intrinsic mathematical properties. In geographical applications (when a "level" is a "place") however, these intrinsic mathematical properties conflict with some well-known effects of spatial dependence. Who wins out, "space" or "place?"
It depends! This talk will provide a high-level, conceptual overview of the tensions between how "spatial" and "platial" (i.e. multilevel) models work. I'll discuss some of the results from Wolf et al. (2021) about how these tensions get resolved, and what it means for practitioners working with classical multilevel models that involve geographic levels.
About the Speaker
Senior Lecturer in Quantitative Human Geography at University of Bristol
Levi John Wolf is a Senior Lecturer in Quantitative Human Geography at the University of Bristol, Fellow at the University of Chicago Center for Spatial Data Science, a Fellow at the Alan Turing Institute, and an editor of Environment and Planning B: Urban Analytics and City Science. He works on building better methods and models to understand society and our environment, and has published papers on elections, inequality, gerrymandering, and demographic change. He is heavily involved in the open science movement, maintaining and contributing to a variety of software packages, and is writing an open book on geographic data science (with Serge Rey and Daniel Arribas-Bel): geographicdata.scienceMore about Levi Wolf