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

- Home
- /
- SAS Programming
- /
- General Programming
- /
- How to compute simulation error of a parameter in ...

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
- Highlight
- Email to a Friend
- Report Inappropriate Content

02-26-2014 07:07 PM

I am interested in computing the simulated error for the parameter t in the regression. SAS gives me the regression error ot t which is StdEr I wish to know if sas has an easy way to get it.

THanks

Accepted Solutions

Solution

02-27-2014
08:45 AM

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

Posted in reply to desireatem

02-27-2014 08:45 AM

Would restating the simulation error as sqrt(sum(beta_i - beta_bar)/(N-1)) be correct?

I would feel more comfortable with sqrt(sum((beta_i - beta_bar)**^2)**/(N-1)), so that it is now essentially the standard deviation of the beta_i estimates.

Steve Denham

Message was edited by: Steve Denham

All Replies

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

Posted in reply to desireatem

02-26-2014 07:12 PM

Is your formula above correct?

desireatem wrote:

The simulated error is sqrt (1/N-1(SUM(bete_i-bar(beta)).

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

Posted in reply to Reeza

02-26-2014 07:20 PM

It might not be correctly type. However do you know how to compute the simulated standard error. This is the correct simulation error: SQRT [1/N-1 *SUM(Est(beta_i- bar(beta))] where N=1000 number of replicates.

Solution

02-27-2014
08:45 AM

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

Posted in reply to desireatem

02-27-2014 08:45 AM

Would restating the simulation error as sqrt(sum(beta_i - beta_bar)/(N-1)) be correct?

I would feel more comfortable with sqrt(sum((beta_i - beta_bar)**^2)**/(N-1)), so that it is now essentially the standard deviation of the beta_i estimates.

Steve Denham

Message was edited by: Steve Denham

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

Posted in reply to Reeza

02-27-2014 10:49 AM

If I'm interpreting this correctly,

SUM(bete_i-bar(beta))=0 always, assuming bar(beta) is average of beta.