turn on suggestions

Auto-suggest helps you quickly narrow down your search results by suggesting possible matches as you type.

Showing results for

- JMP User Community
- :
- Discussions
- :
- Discussions
- :
- Simulate responses within defined range

Topic Options

- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Get Direct Link
- Email to a Friend
- Report Inappropriate Content

Jul 25, 2015 9:21 AM
(3248 views)

I have been using the RANDBETWEEN(min,max) function in excel to generate random simulated responses which I paste into the matrix.

**Rather than using the model coefficients to simulate the response variables, can JMP generate "random" numbers within a defined range? What is the drawback of using this method (asides from the obvious - the random values not fitting the model)?**

Thanks!

1 ACCEPTED SOLUTION

Accepted Solutions

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Get Direct Link
- Email to a Friend
- Report Inappropriate Content

acid1c,

Will this do the trick for you?

3 REPLIES

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Get Direct Link
- Email to a Friend
- Report Inappropriate Content

acid1c,

Will this do the trick for you?

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Get Direct Link
- Email to a Friend
- Report Inappropriate Content

Thank you for pointing me in this direction, but I found a better solution. Random Normal is generating numbers with a defined mean and standard deviation. A better choice is to use Random Uniform which generates numbers within a defined min and max range:

*Right click on column > Formula > Random > Random Uniform > Random Uniform(min,max)*

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Get Direct Link
- Email to a Friend
- Report Inappropriate Content

Random uniform does work well with a defined min and max, but it does not have a peaked shape like a normal distribution. If you want a peaked shape, use the Triangular distribution. It has a defined min and max with a mode or peak.

Dan Obermiller