Collider bias undermines our understanding of COVID-19 disease risk and severity.
Griffith GJ, Morris TT, Tudball MJ, Herbert A, Mancano G, Pike L, Sharp GC, Sterne J, Palmer TM, Davey Smith G, Tilling K, Zuccolo L, Davies NM, Hemani G. · 2020
Read Collider bias undermines our understanding of COVID-19 disease risk and severity. by Griffith GJ, Morris TT, Tudball MJ, Herbert A, Mancano G, Pike L, Sharp GC, Sterne J, Palmer TM, Davey Smith G, Tilling K, Zuccolo L, Davies NM, Hemani G. (2020) 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/europmc-pmc7665028.txt.
Description
Griffith and co-authors warn that a sampling flaw can distort COVID-19 research. Many studies draw on people in hospital, people tested, or volunteers. Such samples are not a fair cross-section of the public. The flaw is called collider bias.
When two traits each affect who gets sampled, the sample can show false links between them. Using UK Biobank data, the authors show that tested people were highly selected on many traits. These ranged from genes and behavior to heart risk and body measures. The authors urge better sampling at the design stage, not just fixes after the fact.
Catalog record
| CREATOR | Griffith GJ, Morris TT, Tudball MJ, Herbert A, Mancano G, Pike L, Sharp GC, Sterne J, Palmer TM, Davey Smith G, Tilling K, Zuccolo L, Davies NM, Hemani G. |
|---|---|
| YEAR | 2020 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 75 KB |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |