Am trying to set a few binary/dummy variables against each other, i.e. propensity_to_dance and gender.
I assume that it' ok to be using a binary logistic regression in SPSS (or otherwise) to investigate the interaction on these two variables; I've previously been using that kind of regression to investigate the relationship between binary and linear variables. Is it correct to use this methodology for two binary variables as in the above?
First, why is "propensity to dance" binary? That seems like a mistake. I think it would vary along from people with no propensity to dance (e.g. me) to those who will dance at every opportunity, or even make opportunities).
But, if it has to be binary, then .... logistic regression is OK here; like other forms of regression, it assumes that there is a dependent and an independent variables. Here, I would assume that propensity is the DV and gender the IV; although I can imagine situations in which they would be reversed!
If you just want to look at association between two binary variables, chi-square can be a good method.
