Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: RE: RE: LevenbergMarquardt/summary


From   "Stephen P Jenkins" <stephenj@essex.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: RE: RE: LevenbergMarquardt/summary
Date   Tue, 9 Mar 2004 10:33:16 -0000

If you want to fit a mixture of normals, then I think Stas Kolenikov has
a program for doing this. 
-findit- should locate this


Stephen
-------------------------------------------------------------
Professor Stephen P. Jenkins <stephenj@essex.ac.uk>
Institute for Social and Economic Research
University of Essex, Colchester CO4 3SQ, U.K.
Tel: +44 1206 873374.  Fax: +44 1206 873151.
http://www.iser.essex.ac.uk   


> -----Original Message-----
> From: owner-statalist@hsphsun2.harvard.edu 
> [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Nick Cox
> Sent: 09 March 2004 10:16
> To: statalist@hsphsun2.harvard.edu
> Subject: st: RE: LevenbergMarquardt/summary
> 
> 
> It might be better to set this up as a -ml- problem. 
> 
> The text of Sophia Rabe-Hesketh and Brian Everitt
> discusses the two Gaussians case in detail and poses
> your case as an exercise, with hints for solution. 
> 
> http://www.stata.com/bookstore/statanalyses.html
> 
> Nick 
> n.j.cox@durham.ac.uk 
> 
> Andreas Aschbacher
> 
> > In austrian centre of physics we use Stata to do
> > LevenbergMarquardt(nl-coomand)
> > please look at my posting from january 20th with
> > heading:LevenbergMarquardt
> > short summary :the number of persons who is exposed to a little 
> > dosis-interval /about 0.01 mSv/ yields in sum a curve which 
> is mostly
> > composed of 
> > two sometimes three humps.above each dosis-interval /about 
> > 0.01 mSv/there is
> > the number 
> > of persons as function. with Stata it was possible to show 
> that in 397
> > cases we have the sum of Gau-distributions.the results are 
> > very useful.
> > because of lv-command we can talk here about skewness of our curves.
> > median-test is also used very often.we decided to take Stata 
> > to use for our
> > work becaue it is so easy to split in subgroups and make 
> tests after.
> >                                 -
> > 
> > My question: if I have two Gau-curves to be fitted,it is no
> > problem to find
> > values
> > in Stata.but if I have to find three Gau-curves,I mean to 
> > come from 1) to
> > 2) for
> > example
> > 
> > 1)
> > Ai for i = 1,2.... means amplitude
> > A1	12209.2
> > 1	4.382678
> > delta1	0.3097696
> > A2	21683.69
> > 2	4.200002
> > delta2	0.550282
> > 
> > 2)
> > A1	11509.05
> > 1	4.403567
> > delta1	0.3050716
> > A2	1305.195
> > 2	4.18422
> > delta2	1.100233
> > A3	21540.19
> > 3	4.198081
> > delta3	0.5104234
> > 
> > I need long time to try.with another famous statistical
> > software I have
> > possibility to make 
> > constraints and it takes no long time.
> > I "fear the worst" that someone(my boss?) will ask me during my
> > presentation,if there are add-inns in Stata to use or 
> > user-written-programs that I have
> > this feature.
> > it is a pity that it is not possible for me to come to 2nd 
> > German Stata
> > User's meeting in April.
> 
> *
> *   For searches and help try:
> *   http://www.stata.com/support/faqs/res/findit.html
> *   http://www.stata.com/support/statalist/faq
> *   http://www.ats.ucla.edu/stat/stata/
> 


*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index