Dear fellows !
I want to bring forward
1) f1[x_]:= Exp[-(x-y)^2/(2*(s^2))];
2) f2[x_]:= .1/(x + .1);
3)ff[d_]:=NIntegrate[f1[d-x] f2[x],{x,0,d}];
4) Plot[{f1[x],f2[x],ff[x]},{x,0,10}]
1) bis 4) is mathematica language for convolution-integral
/let's say y= 0 and s = 1 /
in Stata-language.
I'd like to have
integral(f1(d-x)*f2(x))dx from 0 to 0.1 /d = 0.1
integral(f1(d-x)*f2(x))dx from 0 to 0.2 /d = 0.2
.
.
.......................................................... /d = 10
in order to plot my convolution-function - that means :all integral-values
as a function
of my steps;
->I will show you what I did:
~
drop _all
set obs 100
tempname tempd1 tempd2
scalar `tempd1'=0.1
gen double d=.
gen double conv=.
forvalue i=1/100 {
scalar `tempd2'=`i'*`tempd1'
range x 0 `tempd1' 100
gen double y=exp(-(`tempd2'-x)^2/2)*0.1/(x+0.1)
integ y x, gen(Sy)
replace d=`tempd2' in `i'
replace conv=Sy[100] in `i'
drop Sy x y if
}
gen x=d
gen f1=exp(-(`tempd2'-x)^2/2)
gen f2=0.1/(x+0.1)
line f1 x || line f2 x || line conv x
~
I don't know why it does not work !
any advice will be appreciated very much.
andreas aschbacher
--
+++ 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/
