Just wanted to thank everyone for their help, I think I mostly managed to
solve my problem.
--
View this message in context:
http://www.nabble.com/MLE-for-bimodal-distribution-tp22954970p23000785.html
Sent from the R help mailing list archive at Nabble.com.
_
On 08-Apr-09 23:39:36, Ted Harding wrote:
> On 08-Apr-09 22:10:26, Ravi Varadhan wrote:
>> EM algorithm is a better approach for maximum likelihood estimation
>> of finite-mixture models than direct maximization of the mixture
>> log-likelihood. Due to its ascent properties, it is guaranteed to
>>
University
Ph. (410) 502-2619
email: rvarad...@jhmi.edu
- Original Message -
From: ted.hard...@manchester.ac.uk (Ted Harding)
Date: Wednesday, April 8, 2009 7:43 pm
Subject: Re: [R] MLE for bimodal distribution
To: r-h...@stat.math.ethz.ch
> On 08-Apr-09 22:10:26, Ravi Varadhan wro
On 08-Apr-09 22:10:26, Ravi Varadhan wrote:
> EM algorithm is a better approach for maximum likelihood estimation
> of finite-mixture models than direct maximization of the mixture
> log-likelihood. Due to its ascent properties, it is guaranteed to
> converge to a local maximum. By theoretical co
on of Geriatric Medicine and Gerontology
School of Medicine
Johns Hopkins University
Ph. (410) 502-2619
email: rvarad...@jhmi.edu
- Original Message -
From: Bert Gunter
Date: Wednesday, April 8, 2009 4:14 pm
Subject: Re: [R] MLE for bimodal distribution
To: 'Ben Bolker' , r-hel
_nico_ wrote:
Hello everyone,
I'm trying to use mle from package stats4 to fit a bi/multi-modal
distribution to some data, but I have some problems with it.
Here's what I'm doing (for a bimodal distribution):
# Build some fake binormally distributed data, the procedure fails also with
real data
ontology
School of Medicine
Johns Hopkins University
Ph. (410) 502-2619
email: rvarad...@jhmi.edu
- Original Message -----
From: Ben Bolker
Date: Wednesday, April 8, 2009 3:49 pm
Subject: Re: [R] MLE for bimodal distribution
To: r-help@r-project.org
>
>
> _nico_ wrote:
> &g
Ben Bolker wrote:
>
>
> Here's some tweaked code that works.
> [cut]
>
Thanks, that saved me a few headaches. I also find out the answer to my
(dumb) question #5, which is obviously to call f with the returned
parameters or use the logLik function.
I will have a look at the mixture model p
ubject: Re: [R] MLE for bimodal distribution
_nico_ wrote:
>
> Hello everyone,
>
> I'm trying to use mle from package stats4 to fit a bi/multi-modal
> distribution to some data, but I have some problems with it.
> Here's what I'm doing (for a bimodal distribution)
_nico_ wrote:
>
> Hello everyone,
>
> I'm trying to use mle from package stats4 to fit a bi/multi-modal
> distribution to some data, but I have some problems with it.
> Here's what I'm doing (for a bimodal distribution):
>
> # Build some fake binormally distributed data, the procedure fails a
Hello everyone,
I'm trying to use mle from package stats4 to fit a bi/multi-modal
distribution to some data, but I have some problems with it.
Here's what I'm doing (for a bimodal distribution):
# Build some fake binormally distributed data, the procedure fails also with
real data, so the proble
11 matches
Mail list logo
