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
- /
- Analytics
- /
- Stat Procs
- /
- Confidence intervals of a stratified table

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

04-08-2009 10:37 AM

Can anybody give me any insight as to how to write a program that forms confidence intervals for one component from a stratified table? I have a list of stratified dollar amounts in a table, and want a confidence interval for each of those amounts.

Thank you!

Thank you!

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

04-08-2009 11:14 AM

Erin,

Your question isn't very specific about the end goal.

The basic formula for a normal approximation confidence interval for a proportion, p, is

p +- 1.96*SQRT(p(-1p)/n)

If you are looking for some sort of pooled confidence limit, you might be able to get it using PROC LOGISTIC with the STRATA statement. You might also be able to get something useful using PROC FREQ and the CMH option.

Doc Muhlbaier

Duke

Your question isn't very specific about the end goal.

The basic formula for a normal approximation confidence interval for a proportion, p, is

p +- 1.96*SQRT(p(-1p)/n)

If you are looking for some sort of pooled confidence limit, you might be able to get it using PROC LOGISTIC with the STRATA statement. You might also be able to get something useful using PROC FREQ and the CMH option.

Doc Muhlbaier

Duke