A relevant thread from a few years ago where this was discussed:
https://www.stat.math.ethz.ch/pipermail/r-help/2023-August/477904.html
I generally use:
export OPENBLAS_NUM_THREADS=1
export MKL_NUM_THREADS=1
since in my experience the biggest performance gains come from switching to
OpenBLAS /
Dear Zhen,
You can use this with pdDiag(). An example:
library(nlme)
res <- lme(distance ~ age*Sex, random = list(Subject = pdDiag(~ age)),
data=Orthodont)
summary(res)
Best,
Wolfgang
> -Original Message-
> From: R-help On Behalf Of ??
> Sent: Monday, January 8, 2024 12:43
> To: R-hel
Dear Marc,
Plugging the BLUPs into the likelihood isn't going to give you the ll of the
model. You need to integrate over the random effect.
intfun <- function(nu, xi, mi, pred, theta)
dbinom(xi, xi+mi, plogis(nu)) * dnorm(nu, pred, theta)
lli <- rep(NA, nrow(df))
for (i in 1:nrow(df)) {
Ah, super interesting! Thanks for the pointer, Bill.
I might not have seen the issue because I have
export MKL_NUM_THREADS=1
in my .profile, so MKL never goes beyond using one thread on my machine.
That's a potential source of non-reproducibility I have not come across. So the
'wisdom' that on
But I have never seen a case where, on the same machine and using the same math
routines, using the same seed repeatedly generated different values. That is
quite bizarre (the issue I was discussing in the thread is quite simple in
comparison). I tried to reproduce the issue below, but was unabl
For value labels, factor() provides the necessary machinery. For variable
labels, one could make use of comment() (something that not too many people
seem to know about). To illustrate:
# look at the mtcars dataset
mtcars
# turn 'am' into a factor and use labels for the two possible levels ther
How about using the same 'mar' for all plots, but adding an outer margin?
DAX <- EuStockMarkets[, 'DAX']
DAX. <- cbind(DAX, diff(log(DAX)), diff(diff(log(DAX
colnames(DAX.) <- c("DAX", 'vel (%)', 'accel (%)')
head(DAX.)
par(mfrow=c(3,1), mar=c(1,4.5,0,2), oma=c(3,0,1,0))
plot(DAX.[, 1], log=
@Joe: I have S-Plus 6.0 ("Professional Edition Version 6.0.3 Release 2 for
Microsoft Windows : 2001") running here and can't load them there either. Tried
simdat and S-Plus apparently thinks it is a script and then you just get a
garbled up mess. Tried to change it to simdat.sdd and a few other
8 matches
Mail list logo
