On Mon, 2 Feb 2004, Andreas Aschbacher wrote:
> dear fellows !
>
> I have a snappy curve(y(x)) which looks like the sum of two Gau�-functions a
> great and a little
> hump.I use > integ y x,gen(Sy) and line y Sy x < to get the
> integral-function above.
> the result-curve .line Sy x seems to be the "sum" of two nearly straight
> lines with different
> k- values(y = k*x+d) that means from 0 to 5 I have k1 and from 5 to 10 I
> have k2.
> Now I'd like to make linear regression for both
> parts(region1<->k1,region2<->k2)
> in one commandline.Is this possible ?
even though I cant quite follow why you want to do this
the answer to your last question is
gen x1=x*(x<5)
gen x2=x*(x>=5)
regress y x1 x2
Best
Lars
> thank you very much andreas
>
> --
> +++ Mailpower f�r Multimedia-Begeisterte: http://www.gmx.net/topmail +++
> 250 MB Mailbox, 1 GB Online-Festplatte, 100 FreeSMS. Jetzt kostenlos testen!
>
> *
> * 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/
>
..............................................
: Lars Korsholm Ph.D., :
: Department of Statistics :
: University of Southern Denmark :
: Sdr. Boulevard 23A, 2. :
: DK-5000 Odense C :
: Phone +45 6550 3608 (or 3868) :
: Mobil +45 3033 3617 :
: Fax +45 6595 7766 :
: Mail [email protected] :
: Web http://www.biostat.sdu.dk/~korsholm :
:............................................:
*
* 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/
