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
- /
- R-square in logistic regression

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

12-08-2016 02:55 PM

Hello - what does one use for R-square in logistic regression...is it AUC?

Accepted Solutions

Solution

07-26-2017
08:51 AM

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

12-08-2016 10:35 PM

R-square is similar R-square in PROC REG. but it is not AUC -- C statistic

```
proc logistic data=sashelp.class;
model sex=weight height/lackfit rsquare;
run;
```

All Replies

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

12-08-2016 02:25 PM

Hello, is there an R-square in logistic regression? Is this the best goodness of fit or which goodness of fit is better to use?

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

12-08-2016 03:59 PM

There are a number of different model fit statistics available. It also depends on exactly which procedure as several do logistic regression and the nature of your data: Rsquare -2 Log Likelihood, AIC SC Homer-Lemeshow test are some available in Proc Logistic for tests/metrics. Look at the MODEL options.

Solution

07-26-2017
08:51 AM

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

12-08-2016 10:35 PM

R-square is similar R-square in PROC REG. but it is not AUC -- C statistic

```
proc logistic data=sashelp.class;
model sex=weight height/lackfit rsquare;
run;
```