Home > Statistics Every Writer Should Know > The Stats Board > Discusssion
odds ratio in logistic regression
Message posted by Susan Daniels (via 128.173.184.227) on June 19, 2001 at 12:40 PM (ET)
I have a shallow understanding of the odds ratio in logistic regression. I have a significant independent with a sign in the opposite direction than expected. The odds ratio is > 999.99. What does this mean, and how should I proceed?
READERS RESPOND:
(In chronological order. Most recent at the bottom.)
Re: odds ratio in logistic regression
Message posted by JG (via 128.8.22.83) on June 19, 2001 at 1:34 PM (ET)
You have a P>.999 or almost 1.0 . When probability is a dependent variable, we use ln(odds ratio) to do regression analysis and then convert the answer back to probabilities with an appropriate transformation.
Re: odds ratio in logistic regression
Message posted by Susan Daniels (via 128.173.184.227) on June 19, 2001 at 2:08 PM (ET)
Is this result valid? What factors might change the sign on me?
Re: odds ratio in logistic regression
Message posted by JG (via 128.8.23.221) on June 19, 2001 at 6:37 PM (ET)
ln(odds ratio) can be negative - it means that you have a very small probability - below P=.5 we odds ratios less than 1 and negative ln(odds ratio)
Your $5 contribution helps cover part the $500 annual cost of keeping this site online.