Date:         Tue, 4 Oct 2005 09:26:24 -0400
Reply-To:     Venita DePuy <depuy001@NOTES.DUKE.EDU>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         Venita DePuy <depuy001@NOTES.DUKE.EDU>
Subject:      Re: draw a normal distribution (also lognormal)
Comments: To: Jianping Zhu <zhujp98@gmail.com>
In-Reply-To:  <6716d5d0510032132k10b07edau40c3175d509243a7@mail.gmail.com>
Content-Type: text/plain; charset="US-ASCII"

You can also use the method Rene mentioned, in Proc Univariate instead of
Proc Capability.
-Venita

data file1;
do i = 1 to 100;
j = rannor(i);
k = exp(j);
output;
end;

run;
symbol v=circle cv=blue;
*to test distribution;
proc univariate data=file1;
var j k;
histogram;
QQPLOT / normal (mu=est sigma=est);
run;


Thanks.
one more question, how can i use QQ plot to check the mormality of
generated
sample in this case?
 Thanks again.

 On 10/4/05, Venita DePuy <depuy001@notes.duke.edu> wrote:
>
> I believe the following will create a normal distribution (with mean 0
and
> std dev 1) Note that it looks much more normal if you use 1000 points,
> etc.
> If you want to get particular, you can have Proc Univariate draw in
lines
> for what a normal and/or lognormal distribution, with the mean/std dev
of
> the data, should look like.
>
>
> Hope this helps.
> j is normally distributed.
> k is lognormally distributed.
>
> You can do a simple transformation for a lognormal distribution.
>
>