SAS Optimization, and SAS Simulation Studio

turn on suggestions

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

Showing results for

Find a Community

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
- Permalink
- Email to a Friend
- Report Inappropriate Content

06-19-2012 04:38 PM

Hi,

I am trying to select 200 points from a pool of 1000 points which are nearest to the line say y = x using least squares. and my constraint is that the average of the values of the 200 points should be below a given value. How can i formulate this model using Proc optmodel?

I am not sure how i write the objective function in this case. I thought it should be like

min f = {sum i in 1..200} (x* - y )**2*

but in the above objective function, there is nothing to minimize, it just calculates the sum of least squares of first 200 obs. I am confused on how to tackle this. Plz help.

Thank you!

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content

Posted in reply to hckadali

06-19-2012 05:11 PM

"the average of the values of the 200 points should be below a given value" ? The average of what value, x, y, SSQ?

PG

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content

Posted in reply to PGStats

06-19-2012 05:22 PM

There is one more column, say 'z'.

Average of (y/z) of those 200 points should be less than some given value.

If i am correct in representing in SAS OPT model notation:

con constraint: {sum i in 1..200} (y*/z ) / 200 <= 0.60 *