Search Archives

I can't find Hmisc in the contributed package libraries but I can find Design which requires it. I assume it has been missed. Ken

On 31/01/2009, at 12:58 AM, Ian Dworkin wrote: > It is worth noting that MCMCglmm is not yet available for OS X. > It compiles from source, so it is just a delay in the build. Ken >

A new package 'randomLCA' is available on CRAN. Its main purpose is to fit latent class models with random effects, such as those used in diagnostic testing. This methodology can also be applied in other areas. It also fits standard...

On 18/09/2010, at 7:53 AM, steven mosher wrote: > > So, It appears that I have to install a compiler. Looking at Xcode the > package that was available required an OS upgrade > is Xcode the only option or is...

I have an optimisation that gets a different result on an AMD based PC to a G5 iMac. I suspect underflow (it involves small probabilitiies that need to be summed so can't be logged, next step is to rescale...

I?ve received an e-mail from Kurt Hornik, that they are going to remove the doRNG package because of build problems. Looking at it, it is only because the Rmpi package fails to build on MacOS and hence any...

I am trying to build aqua R on 10.2.1 using the gcc compilers from Jans site (I would have used fink except they don't have a simple system under 10.2 yet) but am getting error: linking...

A new package 'randomLCA' is available on CRAN. Its main purpose is to fit latent class models with random effects, such as those used in diagnostic testing. This methodology can also be applied in other areas. It also fits standard...

On 26/01/2006, at 6:36 PM, Simon Urbanek <simon.urbanek at r- project.org> wrote: > As of performance, don't hold your breath, > Core Duo is fast for daily use, but not particularly good at > computing like BLAS...

Congratulations on an excellent program. A minor bug, if while executing a R source file, I start up the HTML help system and then close it, the STOP icon in the console window remains dimmed. The only way of stopping...

On 15/01/2008, at 2:59 AM, Zhong, Xiao wrote: > Hello, > > I am working on a project that uses glmm. I would like to consider b- > spline in the original glmm but I couldn't find how to add...

Patrick Connolly wrote > > Somehow, southern hemisphere sites aren't taken as seriously as those > from that other hemisphere. Is there a word for that type of bias? > There is a more simple explanation. If a page isn't linked to...

Hi, Runs perfectly for me, using the standard R download. Ken On 30/10/2007, at 5:54 AM, Ken Nussear wrote: > Hi > > I saw a couple of posts mentioning a solution for using R in Leopard. > Seems like the...

I'm maximising a reasonably complex function using nlme (version 3.1-65, have also tried 3.1-66) and am having trouble with fixed parameter estimates slightly away from the maximum of the log likelihood. I have profiled the...

Still missing. Ken > On 23 Jul 2020, at 11:06 pm, G?bor Cs?rdi <csardi.gabor at gmail.com> wrote: > > Hi Simon, > > I wonder if the tarballs and the installers for 4.0 and 4.1 are > missing from...

On 19/04/2008, at 4:33 AM, marcioestat at pop.com.br wrote: > > > Hi listers, > > Could anyone please provide to me any reference, articles or books, > about the GLM and GEE with examples with R.... > I have already looked...

3.3 built for Mavericks at http://r.research.att.com should work. Ken > On 6 Sep 2018, at 4:27 am, Braden Justice <Braden at bradenjustice.com> wrote: > > Hello, I can?t seem to find a version that works...

summary(fm1) Obtaining a copy of Pinheiro and Bates is strongly recommended. Ken On 24/09/2009, at 8:28 PM, FMH wrote: > Dear All, > > Herewith, is a sample of mixed model command from the help menu. > > fm1 <- lme(distance...

On 24/01/2007, at 12:03 PM, Paul Gowder wrote: > Hi everyone... > > Here's a good one. I'm using the R installation for mac osx. An > overly helpful friend tried to download a couple of packages for me...

On 01/05/2008, at 11:28 PM, Sebastian P. Luque wrote: > > which I presume is due to the fact that the data are unreplicated, > i.e. individuals get each treatment only once. No. Due to not having a random...