Should We Abandon the t -Test in the Analysis of Gene Expression Microarray Data: A Comparison of Variance Modeling Strategies
Marine Jeanmougin, Aurelien de Reynies, Laetitia Marisa et al. · 2010
Read Should We Abandon the t -Test in the Analysis of Gene Expression Microarray Data: A Comparison of Variance Modeling Strategies by Marine Jeanmougin, Aurelien de Reynies, Laetitia Marisa et al. (2010) 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/plos-pone-0012336.txt.
Description
Marine Jeanmougin, Aurelien de Reynies, Laetitia Marisa, and co-authors asked if gene studies should drop the classic t-test, in PLOS ONE in 2010. Labs compare two groups gene by gene with a t-test. It is the routine first pass over microarray data. Yet the test draws criticism in this setting. Each gene's spread is measured from few samples. At the same time, thousands of tests run at once.
They compared the plain test with smarter strategies. The new strategies model gene variance with more care. They borrow strength across genes to do so. The verdict guides daily choices in thousands of labs. Small choices at this scale have huge effects. They decide which genes get years of follow-up work. An answer based on proof has outsized value here.
Catalog record
| CREATOR | Marine Jeanmougin, Aurelien de Reynies, Laetitia Marisa et al. |
|---|---|
| YEAR | 2010 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 34 KB |
| LICENSE | Creative Commons Attribution License |
| RIGHTS | CC BY |
| SOURCE | PLOS ONE |
Source: https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0012336