On Mon, 18 Nov 2002 11:54:30 -0000 Keith Farnsworth
<[email protected]> wrote:
> Hi,
> I have a large set of short time-series (one for each patient) of about 2000 patients. The patient is identified by a record number rc and the time series data point by pnt. I have used
>
> sort rc pnt
> by rc : regress dt lv
>
> to obtain a lin. regression for each patient (as an example - the real thing will use non-linear regression).
>
> I am interested in the results of all these little regressions (coefficients, P values and Rsquared). My question is - can I extract these from the regression results (which go to the screen) in order to put them in a new variable. The aim is to summarise each patient's time series using the results of their regression model.
>
> Like this:
>
> Patient Rsquare const P coef P
>
>
> Is this possible? Or do I have to write the regression method explicitly (ie not using regress)?
-help statsby- may help you
-findit statsby- provides a longer menu of possibilities (including
Roger Newson's -parmest-)
Stephen
----------------------
Professor Stephen P. Jenkins <[email protected]>
Institute for Social and Economic Research (ISER)
University of Essex, Colchester, CO4 3SQ, UK
Tel: +44 (0)1206 873374. Fax: +44 (0)1206 873151.
http://www.iser.essex.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/
