Method for continuous predictor and dichotomous dependent variable

[Ciara Kate]

Hi everyone,

I am working on a research project asking: Do lower rates of school satisfaction and school engagement influence students’ suspension and expulsion?

School satisfaction and school engagement are the independent variables and are continuous (likert scale strongly disagree to strongly agree)

Suspension and expulsion are ever/never dichotomous variables.

Would I use an ordinal logistic regression? If so how would I go about that?

[Joseph Coveney]

If you want to consider expulsion to be a more severe form of suspension, then you could use ordered-categorical regression methods, yes. You could code punishment meted out as, say, 1 for suspension and 2 for expulsion, and 0 for neither.

The two explanatory variables are not continuous, unless you're actually using a sumscore (summation of two sets of individual ordered-categorical questionnaire items to form each of the two Likert scales, one for satisfaction and the other for engagement). If they're individual questionnaire items, then you'd included them in the regression model as factor variables.

You might want to also look into exogeneity.