
109
5
Testing the Parallel Regression Assumption
Parallel ordered regression models share a common assumption, which is that the effects
of independent variables do not vary across cutpoint equations. We refer to this as the
parallel regression assumption, and for logit models it is also known as the “proportional
odds” assumption (McCullagh 1980). We provide an illustration of the parallel regression
assumption for cumulative models in Figure5.1. In the graph on the left, the cumulative
probability curves are parallel, whereas in the graph on the right they are not. The paral-
lel regression assumption is very useful because it produces a rel ...