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
- /
- Logistic regression - "unique profiles"

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

06-20-2016 09:16 AM

Hello,

I am doing logistic regression in R on a binary dependent variable with only one independent variable. I found the odd ratio as 0.99 for an outcomes. This can be shown in following. Odds ratio is defined as, ratio_odds(H) = Probability(X=H) / (1-Probability(X=H)). As given earlier ratio_odds (H) = 0.99 which implies that the probability (X=H) = 0.497 which is close to 50% probability. This implies that the probability for having a H cases or non H cases 50% under the given condition of independent variable. This does not seem realistic from the data as only ~20% are found as H cases. Please give clarifications and proper explanations of this kind of cases in logistic regression.

Thanks all for your help!

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

06-20-2016 09:47 AM

If you're using R, why are you posting to a SAS forum? Casting a wider net for an answer to your question?

IMO a question like this should be posted on stats.stackexchange.com

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

06-20-2016 10:52 PM

1)Maybe you missed some important independent variables . 2)Maybe the Scale for independent variable is too small . E.X. the dose of medication : 1ml v.s 100ml . Check PROC LOGISTIC 's UNIT statement. 3)Maybe there are some none-linear effect between independent variable and dependent variables. Check PROC LOGISTIC 's EFFECT statement. 4)Why not use Decision Tree or Random Forest in R ?