Variable selection-combined causal mediation analysis for continuous treatments with application to large-dimensional biomedical data
Yajing Zhou, Kecheng Wei, Yahang Liu, Zhaoyang Li, Chen Huang, Guoyou Qin, Yongfu Yu · 2026
Read Variable selection-combined causal mediation analysis for continuous treatments with application to large-dimensional biomedical data by Yajing Zhou, Kecheng Wei, Yahang Liu, Zhaoyang Li, Chen Huang, Guoyou Qin, Yongfu Yu (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/PMC13327524.txt.
Description
Yajing Zhou and co-authors propose a new statistics method in a 2026 article on causal mediation with continuous treatments. Standard tools handle yes-or-no treatments well, but dose-like treatments plus thousands of possible background factors strain them. Their framework joins variable selection with propensity modeling in a weighted semiparametric design.
Tests in simulation showed better variable picking and more efficient estimates than rival regularization methods, because outcome-linked factors were kept and noise factors dropped. The team then applied the method to UK Biobank data, measuring how much of the link between diabetes risk and cancer runs through apolipoprotein B levels. The approach offers a steadier balance of accuracy, clarity, and strength for large biomedical datasets.
Catalog record
| CREATOR | Yajing Zhou, Kecheng Wei, Yahang Liu, Zhaoyang Li, Chen Huang, Guoyou Qin, Yongfu Yu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 90947 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |