Dear fellows !
maybe the following program is useful for someone:
/ computing convolution-integral and cumulative-function /
I seek for possibilities to show that dosis-distributions in population
are composed via convolution of two functions(lognormal ?)
one function represents background - that is radioactivity which is
always around us and not-naturally radioactivity which is for example
radioactivity in a hospital.
physically both allotments are the sum - but !!! probability-distribution in
human-population
is - as we all suppose - composed via convolution.(Bayes-statistic)
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~+
clear
set more off
set obs 100
gen d1 =.
scalar m1 = 3
scalar m2 = 3.5
forvalues i = 1(1)100 {
gen x = [_n]
gen x1 = x*.1
local j = `i' * .1
if `i' == 1 {
local j = .11
di `j'
}
di `j'
di `j'
gen double y = exp(-(log((`j') - x1) - m1 )^2/2) *exp(-(log((`j') - x1) -
m2)^2/2)
/standard-deviation = 1 for both /
replace y = 0 if x1 > `j'
di `j'
integ y x1 ,gen(Sy)
replace d1 = Sy if [_n] == `i'
drop Sy y x x1
}
gen x = [_n]
gen x1 = x*.1
integ d1 x1,gen(Sy_1)
twoway line d1 x1||line Sy_1 x1
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
greetings from austria
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/
