Hi All,
I get the error and output below when running mixed models in phyreg. Anyone
has an idea of what does this mean? Data consists of one continuous and one
categorical independent variables. I am interested in testing their effects and
interaction. There’s no missing data, and data are normally distributed.
Thank y’all.
-Ivalu
This is the command:
m2 <- phyreg(var1~ var2, test= “cat1", data=new.data, phydata= phyconverted
$phy, heightsdata= phyconverted$hts)
This is the error and output:
Some ftriple is NA
Called from: findmax(lorho, hirho, minrho, errrho)
Browse[1]>
debug: surround <- function() {
while ((ftriple[1] > ftriple[2]) && (xtriple[3] > xmin)) {
newxlo <- xtriple[1]^2/xtriple[2]
newflo <- getlik(newxlo)
xtriple[3] <<- xtriple[2]
xtriple[2] <<- xtriple[1]
xtriple[1] <<- newxlo
ftriple[3] <<- ftriple[2]
ftriple[2] <<- ftriple[1]
ftriple[1] <<- newflo
}
while (ftriple[3] > ftriple[2]) {
newxhi <- xtriple[3]^2/xtriple[2]
newfhi <- getlik(newxhi)
xtriple[1] <<- xtriple[2]
xtriple[2] <<- xtriple[3]
xtriple[3] <<- newxhi
ftriple[1] <<- ftriple[2]
ftriple[2] <<- ftriple[3]
ftriple[3] <<- newfhi
}
}
Browse[2]>
debug: try <- function(xtriple, ftriple, xmid, fmid, lopos, hipos) {
if (fmid > ftriple[2]) {
xtriplo <- xtriple[lopos]
xtriphi <- xtriple[hipos]
xtriple[1] <<- xtriplo
xtriple[2] <<- xmid
xtriple[3] <<- xtriphi
ftriplo <- ftriple[lopos]
ftriphi <- ftriple[hipos]
ftriple[1] <<- ftriplo
ftriple[2] <<- fmid
ftriple[3] <<- ftriphi
return(1)
}
else {
return(0)
}
}
Browse[2]>
debug: centre <- function(xtriple, ftriple, lxmid, lfmid, rxmid, rfmid) {
xtriple[1] <<- lxmid
xtriple[3] <<- rxmid
ftriple[1] <<- lfmid
ftriple[3] <<- rfmid
}
Browse[2]>
debug: bizarretry <- surround()
Browse[2]>
Error in while ((ftriple[1] > ftriple[2]) && (xtriple[3] > xmin)) { :
missing value where TRUE/FALSE needed
In addition: Warning messages:
1: In log(ssterm) : NaNs produced
2: In log(ssterm) : NaNs produced
3: In log(ssterm) : NaNs produced
_______________________________________________
R-sig-phylo mailing list - R-sig-phylo@r-project.org
https://stat.ethz.ch/mailman/listinfo/r-sig-phylo
Searchable archive at http://www.mail-archive.com/r-sig-phylo@r-project.org/
