[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: Code for the algorithm EM
From: |
Thomas Shores |
Subject: |
Re: Code for the algorithm EM |
Date: |
Fri, 14 Sep 2007 09:14:01 -0500 |
User-agent: |
KMail/1.9.7 |
On Friday 14 September 2007, Thomas Weber wrote:
> Am Donnerstag, den 13.09.2007, 21:48 -0500 schrieb Thomas Shores:
> > There may be, but I'm not aware of it. It so happens I needed
> > such a program a few months ago, so I wrote a simple version of
> > it. Go to my public directory
> >
> > http://www.math.unl.edu/~tshores1/Public/
> >
> > then step into the OctaveFiles directory. The program you want
> > is in the Statistics subdirectory.
> >
> > I have a bunch of useful programs there (e.g., an unconstrained
> > optimization suite of programs, some of my own research files in
> > which I've used Octave, etc), but haven't found time to dress
> > them up for submission to an Octave respository. Browse and
> > enjoy, but as always, caveat emptor.
>
> Please add a license to your files. Interested parties might then
> add them to a repository (if the license permits it, that it).
>
> Thomas
>
>
> _______________________________________________
> Help-octave mailing list
> address@hidden
> https://www.cae.wisc.edu/mailman/listinfo/help-octave
I'll be glad to. Would someone suggest a (concise, if there is one!)
GPL license statement that I can sew into these files? BTW, in
regard to Soren Hauberg's comments, specifically the EM algorithm I
wrote converts an input data matrix X with some NaN entries in
various columns into a full matrix Xtilde with conditional estimates
for the missing data computed from MLE estimates of mean and
covariance.
Thomas Shores