3 papers
stat.ME2025
Correlated Confounding Variables Are Not Easily Controlled for in Large Survey Research
William H. Press
Results in epidemiology and social science often require the removal of confounding effects from measurements of the pairwise correlation of variables in survey data. This is typic…
cs.GL2025
LLM Architecture, Scaling Laws, and Economics: A Quick Summary
William H. Press
The current standard architecture of Large Language Models (LLMs) with QKV self-attention is briefly summarized, including the architecture of a typical Transformer. Scaling laws f…
stat.AP2024
"Minus-One" Data Prediction Generates Synthetic Census Data with Good Crosstabulation Fidelity
William H. Press
We propose to capture relevant statistical associations in a dataset of categorical survey responses by a method, here termed MODP, that "learns" a probabilistic prediction functio…