Rao-Scott chi square tests were used to test for differences in demographic variables between POUD and No POUD groups within each of the three multi-year time periods. To assess the between-group difference in odds for each illegal behavior within each of the three multi-year periods, we modeled each illegal behavior as a function of POUD status while adjusting for covariates. The resultant between-group AORs reflected the change in odds for each illegal behavior attributable to POUD within a particular time period.
