Bayesian joint and individual component regression for multigroup physiological data
Muhammed Kara, Mehmet Ali Cengiz, Emre Dünder, Talat Şenel · 2026
Read Bayesian joint and individual component regression for multigroup physiological data by Muhammed Kara, Mehmet Ali Cengiz, Emre Dünder, Talat Şenel (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-13212647.txt.
Description
Muhammed Kara, Mehmet Ali Cengiz, Emre Dünder, and Talat Şenel present a 2026 paper on a Bayesian upgrade to a regression method for grouped body data. Populations like patients or athletes split into subgroups that share some patterns and differ in others. The existing method separates shared from group-specific components but cannot express uncertainty or use prior knowledge. The Bayesian version adds full probability distributions over its answers, with intervals that show how sure the model is.
Estimated by simulation sampling, the method was tested on synthetic scenarios and on a public data set of elite athletes' physical and blood measures. It beat traditional approaches on prediction accuracy, interpretability, and robustness, especially where samples are small. The authors pitch it for medical imaging and other fields with naturally mixed groups. Uncertainty, they argue, is not a luxury in such data.
Catalog record
| CREATOR | Muhammed Kara, Mehmet Ali Cengiz, Emre Dünder, Talat Şenel |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 63 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |