You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
ash does not return logLR i.e. if res=ash(...), there is no res$logLR
I have data where this happens: load("/mnt/lustre/home/epantaleo/src/multiseq/local/testing.pipeline.RData") library(multiseq) #pull the most recent version zdat.ash = ash(zdat[3,ind], zdat[4,ind], prior=prior, multiseqoutput=TRUE, pointmass=pointmass, nullcheck=nullcheck, gridmult=gridmult, mixsd=mixsd, VB=VB, onlylogLR=onlylogLR, g=set.fitted.g[[j]]) zdat.ash$logLR
while (using the same loaded data) ash returns logLR: zdat.rate.ash = ash(zdat.rate[3], zdat.rate[4], prior=prior, pointmass=pointmass, nullcheck=nullcheck, gridmult=gridmult, mixsd=mixsd, VB=VB, onlylogLR=onlylogLR, g=set.fitted.g[[J+1]]) zdat.rate.ash$logLR
it seems that get_loglik returns penalized likelihood when prior is specified. check if this is desired behaviour.
The text was updated successfully, but these errors were encountered: