Turn on suggestions

Auto-suggest helps you quickly narrow down your search results by suggesting possible matches as you type.

Showing results for

- JMP User Community
- :
- Discussions
- :
- Discussions
- :
- How to check for multicollinearity in Ordinal 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
- Get Direct Link
- Email to a Friend
- Report Inappropriate Content

Aug 22, 2016 8:07 AM
(4578 views)

I have an ordinal logistic regression model with 12 continuous independent variables. How can I check for multicollinearity of the independent variables (I can find anything on VIF’s for ordinal logistic models)?

1 ACCEPTED SOLUTION

Accepted Solutions

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Get Direct Link
- Email to a Friend
- Report Inappropriate Content

VIF uses the independent variables only, not the dependent variable. So you can just set your DV from ordinal to continuous and run the standard least squares fit to get the VIFs.

2 REPLIES 2

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Get Direct Link
- Email to a Friend
- Report Inappropriate Content

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Get Direct Link
- Email to a Friend
- Report Inappropriate Content

Re: How to check for multicollinearity in Ordinal logistic regression

Thanks for your reply. I thought so too after looking at the formula for computing VIF's...but I ran two models with two different dependent variables and got different (but similar) VIF's...so I thought I must be missing something...so I went back to these models again and realized the second dependent variable had about 200 missing values so that explains the different VIF's.