Skip to main content
3 votes

Multiple logistic regression with ordinal predictors

If your predictors have a natural order to them, then treating them as more continuous makes more sense, and can be interpreted much like any other predictor in a regression. The problem with treating ...
Shawn Hemelstrand's user avatar
2 votes

Multivariable analysis for an ordinal dependent variable

It is crucial to select a good method for checking the proportional odds (PO) assumption. Which method did you use? Please note that the Bland test is very anti-conservative and that SAS should not ...
Frank Harrell's user avatar
1 vote

Clustering an ordinal variable with unequal interval size

There are different kinds of ordinal variables. Your variable has an underlying ratio scaled variable age and therefore holds more quantitative information than ordinal variables where no such ...
Christian Hennig's user avatar

Only top scored, non community-wiki answers of a minimum length are eligible