BookmarkSubscribeRSS Feed
deleted_user
Not applicable
Hi everyone,

I have a question. Is possible to generate a random numbers from a normal and T distribution with a given minimum and maximum possible values?

For example, given the following parameters: a minimum possible value of -15, a maximum of 40, a mean of 9.5, and a variance of 50...

What is a correct SAS code so I can obtain a pseudo-population with these parameters using both the RANNOR and the RAND functions?

In other words how can I obtain a pseudo-population whose parameters can be similar to the "real population" under study using RANNOR and RAND functions?

Thanks in advance for your help.
3 REPLIES 3
art297
Opal | Level 21
Caramel,

According to the following SUGI 31 paper, a macro exists that does what you are looking to accomplish:

http://www2.sas.com/proceedings/sugi31/198-31.pdf

However, I've been unable to obtain a copy of that macro. If anyone has it, I'd appreciate knowing how to find it.

Art
Doc_Duke
Rhodochrosite | Level 12
Art,

It looks like the author is still at Sanofi-Aventis. Have you tried to e-mail or call her directly.

Someone else was looking for the macro on SAS-L a couple of years ago, but had no follow-up.

Doc
art297
Opal | Level 21
Doc,

Yes, I both saw that post and emailed the paper's author the same day as I posted my response to the current thread. If she resonds, I'll post the answer here.

Art

hackathon24-white-horiz.png

The 2025 SAS Hackathon has begun!

It's finally time to hack! Remember to visit the SAS Hacker's Hub regularly for news and updates.

Latest Updates

How to Concatenate Values

Learn how use the CAT functions in SAS to join values from multiple variables into a single value.

Find more tutorials on the SAS Users YouTube channel.

SAS Training: Just a Click Away

 Ready to level-up your skills? Choose your own adventure.

Browse our catalog!

Discussion stats
  • 3 replies
  • 1667 views
  • 0 likes
  • 3 in conversation