Date:         Sun, 28 Jan 2007 13:06:49 -0500
Reply-To:     "data _null_;" <datanull@GMAIL.COM>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         "data _null_;" <datanull@GMAIL.COM>
Subject:      Re: ranuni - simulation data help
Comments: To: Keith Wright <kwright8@att.net>
In-Reply-To:  <000d01c74254$d6c24350$2301a8c0@KeithWright>
Content-Type: text/plain; charset=ISO-8859-1; format=flowed

Actually I don't think you have done anything wrong.  You have a small
random sample that is very close to you desired percentages.  Isn't
that what you want?  You can get closer to the percents by increasing
N.  Run it to 10K plus and see what you get.  The RANTBL function will
make it easier.

On 1/27/07, Keith Wright <kwright8@att.net> wrote:
> Please help.  I am new to SAS, and I am trying to generate 300 observations with specific proportions based on education level.
>
> I would like for education level to equal 1:  40% of the time, 2:  20% of the time, 3:  10% of the time, 4:  5% of the time an 5:  25% of the time.  My code is below, but it is giving me the following, please advise where I am going wrong....
>
> I am getting the following  for education level               1: 41.33     2: 16.67     3:  9.67    4: 7.33    5: 25
>
>
> data k1; drop num;
>
> do id = 1 to 300;
>
> num = ranuni(0);
>
> if num lt .4 then educ_lev = 1;
>
> else if num ge .4 & num lt .6 then educ_lev = 2;
>
> else if num ge .6 & num lt .7 then educ_lev = 3;
>
> else if num ge .7 & num lt .75 then educ_lev = 4;
>
> else educ_lev = 5;
>
> output;
>
> end;
>
>
>
> Thanks
>
> Keith D Wright
> Georgia State Univ.
> Graduate Research Assistant
>