During week 9 , we looked at a number of combinations of logistic regression, different types of explanatory variables. For this example, let’s look at a dataset where our outcome or response variable has more than 2 levels, a proportional odds model. The coding we used with Proc Logistic is the same you would use here.
This example has males and females, a number of them have been placed on an active trial whereas others have been placed on a placebo trial. The outcome variable is called improve and has been classified into 3 levels: marked improvement, some improvement, or no improvement. For this example I will provide you with the raw data, you will need to do “something” to the data before analyzing it.
Is there a different in improvement for individuals on active vs placebo and is there a gender effect?