I am astounded how hard this has been to google! Even with quote marks, everything is coming back as logistic regression, but this is where the outcome is binary no? I'm looking for help on how to run it the other way round, as in the title. What analysis is needed in SPSS please?
Never mind, I was overcomplicating things. As I was scaling back, I didn't realise, I essentially have two groups now, and can just use a t test. Problem solved!
Hello John,
I'm glad you were able to resolve your own query satisfactorily! Just to show that there's more than one way to answer the same question, any of these approaches could also have been selected:
1. one-way anova (IV is nominal/categorical, with two or more levels; DV is interval or ratio strength / metric / continuous);
2. ordinary least squares regression (IV is dummy coded into c - 1 variates, where c is the number of levels of the IV; DV metric). If only two levels, then just code the IV as (0 and 1, or 1 and 2).
3. For the two-group case, test whether the Pearson correlation of group membership (the IV; coded 0/1 or 1/2) with scores on the DV (metric) equals zero. Same result, with respect to significance/non-significance.
Good luck with your work.
This is not so complex. It's interpretation is not so different from ordinary regression. Good luck
- Badges
- Science topic
- Similar topics
- Mathematical Sciences
- Statistics
- Statistical Software
- SPSS