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
- /
- please explain SAS note

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

03-19-2015 10:35 PM

Hi,

When I ran ordered logistic regression for ordinal outcome variable (like modified Rankin scale, 0-6), SAS gave the following note "Measures of association between the observed and predicted values were not calculated because the mean scored predicted probabilities are indistinguishable". Please explain what the note means. Even though note was presented, sas also provided statistical result. Was result correct when note also appeared? If not be correct, how do I deal with the issue? Thank you very much.

Best

xianwei

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

04-03-2015 01:49 PM

That message occurs when all of the predicted probabilities from the model are very close together as described in the "Rank Correlation of Observed Responses and Predicted Probabilities" section of the LOGISTIC documentation. You can save the predicted probabilities to a data set by using the P= option in the OUTPUT statement. If your model gives all observations very similar predicted probabilities then it clearly is not effective at distinguishing the response levels. Improving the model may require alteration such as treating numeric, ordinal categorical predictors as continuous or adding other predictors. If one of your parameter estimates is extremely large, then the computation of predicted probabilities may be dominated by it. This can result in all predicted probabilities being almost identical, causing this note. If some parameter estimates (or their standard errors) are very large, then you may need to remove them from the model.