I am doing an analysis of my dissertation and wanted to correlate continuous variable (age) and a categorical variable (education-BS, MS, PhD), but not sure which statistics to use.
For Correlation Analysis between two Variables:
Pearson r (IV and DV are Continuous level)
Point Biserial Correlation (IV: Categorical variable with Two categories/Binary; DV: Continuous)
Eta Correlation (IV: Categorical varibale with three or more Categories; DV: Continuous)
Spearman Correlation can be used in either ordinal or interval/ratio scales variables. It is a non parametric Version of Pearson r.
If your objective is prediction, We have what we call Multinomial logistic regression is used to predict a nominal dependent variable given one or more independent variables. It allows us for a dependent variable with more than two categories.
Of course, each of the test has assumptions need to consider/check if your data are fit in on those particular statistical tests.
Best regards,
- Badges
- Science topic