<>
-cumul- takes given values and forms the cumulative distribution function.
These values could be distributed according to any density. -normal- gives
you the cumulative of the normal, and -normalden- gives you the density
function of the normal.
*************
clear*
set obs 10000
gen x=-5+10*runiform()
gen z=normalden(x)
cumul z, gen(cumz)
line z x, sort name(den, replace) /*
*/ nodraw
gen y=rnormal()
cumul y, gen(cumy)
line cumy y, sort name(cumul, replace) /*
*/ nodraw
gr combine den cumul
*************
Note the -egen, std()- function for your standardization purposes (such as
your x and z)...
HTH
Martin
-----Ursprüngliche Nachricht-----
Von: [email protected]
[mailto:[email protected]] Im Auftrag von Evans Jadotte
Gesendet: Dienstag, 13. Oktober 2009 16:01
An: [email protected]
Betreff: Re: st: AW: Hello listers
Martin Weiss wrote:
> <>
>
> Not sure what "...cumulative standard normal distribution of a variable"
> means, but maybe this will help:
>
> *************
> tw (function normal(x), range(-5 5))
> *************
>
>
>
> HTH
> Martin
>
>
> -----Ursprüngliche Nachricht-----
> Von: [email protected]
> [mailto:[email protected]] Im Auftrag von Evans Jadotte
> Gesendet: Dienstag, 13. Oktober 2009 15:20
> An: [email protected]
> Betreff: st: Hello listers
>
> Hi statalisters,
>
> I have a very simple and maybe stupid question, hope someone can help. I
> am trying to get the correct syntax for /_normal_ /to get the
> cumulative standard normal distribution of a variable. Any help?
>
> EJ
> *
> * For searches and help try:
> * http://www.stata.com/help.cgi?search
> * http://www.stata.com/support/statalist/faq
> * http://www.ats.ucla.edu/stat/stata/
>
>
> *
> * For searches and help try:
> * http://www.stata.com/help.cgi?search
> * http://www.stata.com/support/statalist/faq
> * http://www.ats.ucla.edu/stat/stata/
>
Thanks Martin,
Sorry for not being clear on this list. What I am trying to calculate is
, cumulative density of the standard normal or the standard normal
density, respectively. I was trying with
cumul x, gen(y) // x = ((z-m)/sqrt(s))
but what I am getting is not consistent. By the way, does /cumul/ do the
same job as normal(.) or normalden(.) in Stata?
Thanks in advance,
EJ
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/