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

st: NL (not your favorite math equations editor)


From   Simon Moore <mooresc2@cardiff.ac.uk>
To   statalist@hsphsun2.harvard.edu
Subject   st: NL (not your favorite math equations editor)
Date   Fri, 17 Sep 2004 12:12:14 +0100

Many thanks for your quick response and apologies for the misleading
'Subject' line.

Regards
Simon

Friday, September 17, 2004, 11:34:07 AM, you wrote:

NC> Yes, but it is not I think wired into any program. 

NC> For example, you could split your data randomly 

NC> gen fit = uniform() > 0.5 

NC> and then fit the model to one subset 

NC> nl ... if fit 

NC> and then look at predictions for the other: 

NC> ... if !fit 

NC> Nick 
NC> n.j.cox@durham.ac.uk 

NC> Simon Moore
 
>> I am hoping to use non-linear least squares (nl) in Stata v8.0. The
>> analyses are relatively straight forward (nl exp2 var1 var2). However
>> it would be nice if I could perform some form of split half analysis
>> (i.e. fit the model to one half of the dataset and then see how it
>> predicts on the other half). Is there a means of achieving this in
>> Stata?

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



-- 
Best regards,
 Simon                            mailto:mooresc2@cardiff.ac.uk

*
*   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