Whit Armstrong

I've done a bunch of work on it, and the newer version is almost ready. As much as I like my project. I think you should give STAN a shot....

Yes, unfortunately I've broken backwards compatibility w/ my changes. The reason that I find the new way preferable is that in the old version of the code if you were...

I've moved the loglik functions here: https://github.com/armaMCMC/arma-log-likelihood and shur_prod has been updated in that repo. if you still think the semantics need to be chagned (std::forward, etc), then please open...

hmm, what OS and what version of armadillo do you have installed, and what gcc are you using? -Whit On Tue, Jul 3, 2012 at 3:26 AM, jhjourdan [email protected] wrote:...

Just guessing but it looks like that kind of error could happen if an empty matrix is created for the radon dataset. Did you down load the data and modify...

> Ok, sorry, I should have looked into the radon1.cpp file ! > no worries. > > I was assuming test cases were self-contained. BTW, would it be possible >...

Thanks. I'll have a look. It's been a while since I've compiled this package, it could be due to a change in R. What R version are you using?

that happens to us to on Rstudio (not specifically with rcppbugs, but using Rstudio in general). Anyway, I'll have a look a bit later today.

If it is working in the terminal, then I think it is likely a bug in Rstudio. We have seen this issue before on some other object types that Rstudio...

Thanks for the support. The way to use multicore is to use a multithreaded lapack/blas. you will then benefit from the speed up directly in the matrix ops. It's very...