Hey everyone,
I'm working on a research utilizing an ordered Ordinal Logistic Regression (using SPSS and GENLIN system).
Dependent Variable: MRI Category Score (values of 1 or 2 or 3)
Independent Variable: Age (continuous, in days), Seizures during hospitalization (dichotomous)
I'm struggling to interpret the OR it's meaning regarding the DV:
I understand that the OR indicates the odds of being in a higher category - but does it mean regarding going from 1 to 2 OR from 1 to (2 or 3)?
Thank you!
See the attached notes and this link: https://www.bing.com/search?FORM=U528DF&PC=U528&q=How+to+interpret+the+odds+ration+in+biostatistics
Best, David Booth
I want to believe you've done the right thing, the DV is ordinal [3 likert type scale] otherwise you should have used binary regression if the DV is binary.
In SPSS Statistics, an ordinal regression can be carried out using one of two procedures: PLUM and GENLIN. And, in order to capture the ordered nature of these categories(ordinal levels, 1,2 & 3 as in yours), a number of approaches have been developed, based around the use of #cumulative, #adjacent or #continuation categories.
See https://statistics.laerd.com/spss-tutorials/ordinal-regression-using-spss-statistics.php
I think it's important you test if the assumptions are met. Expecially: if there is no multicollinearity, and you have proportional odds.{ meaning that each IV has an identical effect at each cumulative split of the ordinal dependent variable... It is tested in SPSS Statistics using a full likelihood ratio test comparing the fitted location model to a model with varying location parameters.}
**On interpretation of the odds, it's that the odds are statistically not proportional. For instance, the odd of MRI 1 is twice MRI 2, etc.
Having carried out ordinal regression, you will be able to
1. Determine which of your independent variables (if any) have a statistically significant effect on your dependent variable.
2. You will also be able to determine how well your ordinal regression model predicts the dependent variable. Goodness of fit....
Perhabs these are of some help!
https://stats.idre.ucla.edu/spss/dae/ordinal-logistic-regression/
- Badges
- Science topic
- Similar topics
- Philosophy
- Esthetics
- Interpretation