-1

R provides a very powerful package called laplacesdemon for bayesian inference using the laplace distribution. I was wondering if there is any equivalent package for Matlab?

Thanks!

Ajinkya Ghorpade
  • 25
  • 7
  • I find it amusing that the users who have marked this question as off topic have nothing to do with matlab, R or inference which is subject of the question. Not to undermine anyone (or any experts) but seriously IMHO, voting should be reserved to people from same topic areas. I found the answer provided by kamjagin very concise and useful. Rest, I leave it to readers. – Ajinkya Ghorpade Aug 14 '13 at 02:24

1 Answers1

1

The question was a bit short so I'm not sure if this is exactly what you are asking for but here goes:

  1. No - there is no Laplacedemon equivalent in Matlab
  2. Yes - there are lots of Matlab packages that partly overlap with LaplaceDemon. As I don't know exactly what you want to do my recommendation is likely to have a high variance. Having established that I suggest that you take a look at http://becs.aalto.fi/en/research/bayes/gpstuff/ :). If you feel comfortable with using MCMC directly, you can take a look at http://helios.fmi.fi/~lainema/mcmc/. (I believe that matlab has some functions for this directly in their statistics or/and econometrics toolboxes)
  3. You could also run R directly from Matlab http://neurochannels.blogspot.se/2010/05/how-to-run-r-code-in-matlab.html or http://rwiki.sciviews.org/doku.php?id=tips:callingr:matlab
kamjagin
  • 3,614
  • 1
  • 22
  • 24
  • Hi Kamjagin, I continued using R for my implementation but you were right I was looking for high variance model. I was particularly astonished by the number of samplers these guys (laplacesdemon) have implemented. So I was wondering if Matlab has such a toolbox where all the things that can be found in r laplacesdemon package are packaged into one. Most of the times I find the required files from Mathworks distribution but it is annoying to every time stop working and search these things. Anyways, thanks for your help. – Ajinkya Ghorpade Jul 05 '13 at 09:46