and the winning method seems to be a preprint/PeerJ paper from @siminaboca , using swfdr (rather than the flat qvalue approach) to estimate pi_0,i . Seems straightforward enough given the boost in power; why do you suppose it is not more widely used?
-
-
-
Paper is with
@jtleek! It can be hard for people to switch to new methods and in this case there may not be any obvious meta-data covariates to use. In general, adaptive methods also require larger nrs of hypotheses compared to Benjamini-Hochberg in order to get good estimated. - Još 2 druga odgovora
Novi razgovor -
-
-
A great paper that we're citing in an upcoming review article on hypothesis testing methods for data integration!!!!
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.