SPSS 31.0 Versus GPT-5.5: Performance Across Core Epidemiological and Non-parametric Statistics in Medicine and Applied Health Sciences
Frederick F Strale, Rachael German, VeraLucia Mendes-Kramer, Steven B Hammer, Michal Hajek, Walter P Fulbright, Robert Ehrman, Robert Sherwin · 2026
Read SPSS 31.0 Versus GPT-5.5: Performance Across Core Epidemiological and Non-parametric Statistics in Medicine and Applied Health Sciences by Frederick F Strale, Rachael German, VeraLucia Mendes-Kramer, Steven B Hammer, Michal Hajek, Walter P Fulbright, Robert Ehrman, Robert Sherwin (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13606329.txt.
Description
Frederick Strale and co-authors pit a flagship AI model against the statistician's old standard, SPSS, on real health datasets. Researchers increasingly let language models run their numbers, but the software remains the reference for precision and repeatability. The team ran thirteen standard procedures — from chi-square tests and survival curves to regression models — in both systems, feeding the AI the same data names and standard prompts.
Each AI result was compared line by line with the software output for agreement in numbers and method. The study is framed as a replication check on a fast-changing tool: whether a new model generation can be trusted to match the established methodology on core medical statistics.
Catalog record
| CREATOR | Frederick F Strale, Rachael German, VeraLucia Mendes-Kramer, Steven B Hammer, Michal Hajek, Walter P Fulbright, Robert Ehrman, Robert Sherwin |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 78 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |