Statistical Consistency in Artificial Intelligence-Assisted Computations: A Comparison of SPSS 31.0 and GPT-5.5
Frederick F Strale, Rachael M German, VeraLucia Mendes-Kramer, Steven B Hammer, Robert R Ehrman, Robert L Sherwin · 2026
Read Statistical Consistency in Artificial Intelligence-Assisted Computations: A Comparison of SPSS 31.0 and GPT-5.5 by Frederick F Strale, Rachael M German, VeraLucia Mendes-Kramer, Steven B Hammer, Robert R Ehrman, Robert L 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/PMC13384721.txt.
Description
Frederick F. Strale and co-authors compare SPSS 31.0 with GPT-5.5 across common statistical procedures in a 2026 study. Fourteen analyses, from simple descriptions to multi-way variance models, were run on real datasets drawn from published papers. Prompts for the AI model were copied in with the original variable names intact.
Most descriptive and inferential results agreed closely between the two tools, the team reports. Some notable mismatches did appear, though the summary leaves their exact pattern to the full results. The study adds a fresh replication check on whether newer language models can match trusted software for research statistics.
Catalog record
| CREATOR | Frederick F Strale, Rachael M German, VeraLucia Mendes-Kramer, Steven B Hammer, Robert R Ehrman, Robert L Sherwin |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 77967 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |