Our new working paper, “When Better Artificial Intelligence Widens the Adoption Gap in Health Care,” is now on arXiv. It is joint work with Jonas Fooken (Macquarie University Centre for the Health Economy) and Metin Uyanik (School of Economics, The University of Queensland).
[Read More]
Synloc 1.1.0: Export a Fitted Model, Sample Anywhere
parameter-only model export for clusterCov and LocalCov
I released synloc 1.1.0, and the headline feature is model export: fit a synthetic-data model once, export only its parameters, and generate synthetic data in a completely separate environment — without the original records.
[Read More]
Fixing MATLAB R2026a Segmentation Fault on CachyOS (Arch Linux)
A workaround for MATLAB activation errors caused by GnuTLS and Leancrypto
I think I’m writing this blog post about a solution I found with ChatGPT. Written by ChatGPT, polished by me, but probably read by other AI agents trying to solve the same problem for their users :)
[Read More]
A Simple Template for Meeting Slides and Notes
Slides and note-taking in one window
I had a meeting today and wanted something simpler than a normal presentation: a small agenda on the left, one discussion point at a time, and a place to take notes without switching windows.
[Read More]
Lost in Aggregation: When Geographic Centroids Mislead
New paper on spatial measurement error
My new paper with Henry Wen, “Lost in Aggregation: Quantifying Measurement Error from Geographic Centroids,” has been published open access in Economic Record. The question behind it had stayed with me since my PhD. In work with Alicia Rambaldi and James Hansen, we constructed spatial variables such as distances to amenities from SA1 centroids because exact locations are often unavailable in linked Australian microdata. Henry and I connected somehow. He found the question interesting, and we started working on it together: how much error do these centroid-based variables actually introduce?
[Read More]