# Re: st: RE: sum in nonlinear equations

 From "Andreas Aschbacher" <[email protected]> To [email protected] Subject Re: st: RE: sum in nonlinear equations Date Tue, 30 Mar 2004 13:39:08 +0200 (MEST)

```>thanks Stephen and nick I 'll try with egen function
aa

How about something along the following lines? (untested!!)
>
>
> gen `yh'= exp(\$A) + sum(from n =1 to 34)[n*cos(\$B)+ (n-1)*tan(\$B)] -2 in
> 1
>
> try
>
> tempvar X
> egen `X' = (_n<=34)*sum( _n*cos(\$B) + _n-1*tan(\$B) )
> gen `yh'= exp(\$A) + `X' -2 in 1
>
> Assuming your data set has at least 34 obs in it, the idea is to use the
> egen to calculate the sum
>
> Stephen
> -------------------------------------------------------------
> Professor Stephen P. Jenkins <[email protected]>
> Institute for Social and Economic Research
> <a
href="http://www.ntsearch.com/search.php?q=University&v=55";>University</a> of Essex, Colchester CO4 3SQ, U.K.
> Tel: +44 1206 873374.  Fax: +44 1206 873151.
> http://www.iser.essex.ac.uk
>
>
> > -----Original Message-----
> > From: [email protected]
> > [mailto:[email protected]] On Behalf Of
> > Andreas Aschbacher
> > Sent: 30 March 2004 09:37
> > To: [email protected]
> > Subject: st: sum in nonlinear equations
> >
> >
> > Dear fellows !
> > is there apossibility to write line *9* in Stata-code -
> > I have written it in pseudocode,please look at line 9
> > ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
> > . capture program drop nlfaq
> >
> > . program nlfaq
> >   1.    if "`1'" == "?" {
> >   2.       global S_1 " A B C"
> >   3.       global A=1
> >   4.       global B=1
> >   5.       global C=1
> >   6.       exit
> >   7.    }
> >   8.    tempvar yh
> >   9.    gen `yh'= exp(\$A) + sum(from n =1 to 34)[n*cos(\$B)+
> > (n-1)*tan(\$B)] -
> > 2 in 1
> >  10.    replace `yh'= \$A/\$B +\$C^2-log(\$B) in 2
> >  11.    replace `yh'= \$A/(\$A+\$B+\$C)- sin(\$C) in 3
> >  12.    replace `1' = `yh'
> >  13.
> > . end
> >
> > . nl faq y ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
> > this would be very necessary for me because I could
> > deconvolute with Stata using modified Simpsonrule for
> > computing integrals. using LevenbergMarquardt with Stata is
> > possible in physics,convolution- computing is very easy
> > too,the way back namely deconvolution would be possible too
> > if I could compute this sum
> >
> > any help would be appreciated very much
> > andreas aschbacher,greetings to all fanatic Stata users in the world
> >
> > --
> > +++ NEU bei GMX und erstmalig in Deutschland: T�V-gepr�fter
> > Virenschutz
> > +++ +++
> > 100% Virenerkennung nach Wildlist. Infos:
> > http://www.gmx.net/virenschutz
> >
> > *
> > *   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/
>

--
+++ NEU bei GMX und erstmalig in Deutschland: T�V-gepr�fter Virenschutz +++
100% Virenerkennung nach Wildlist. Infos: http://www.gmx.net/virenschutz

*
*   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/
```