Do Individuals with Private Insurance Use More Prescription Drugs?

• Activity Number: 269
• Type: Contributed
• Date/Time: Monday, August 10, 2015 : 2:00 PM to 3:50 PM
• Sponsor: Health Policy Statistics Section
• Author(s): Yan Cheng*
• Companies: The University of British Columbia Centre for Health Services and Policy Research
• Keywords: non-randomized ; propensity score ; stratification ; survey weights ; selection bias

Abstract

We will use three cohorts of respondents from the CCHS 2008 who report having been diagnosed with chronic diseases.Within each cohort,we will conduct the analysis using two-group comparison among drug coverage groups.First,we need to consider baseline covariates strongly associated with the use of medications and having drug coverage.We constructed a propensity score accounting for baseline covariates for each respondent. Then, we divided the respondents into five equal-sized strata based on their propensity scores, and two groups were balanced on the covariates. Moreover, we estimated the probability of using drugs within each stratum and also estimated the overall probability as a weighted average. Finally, we used an indirect poststratification adjustment to the final survey weights to estimate an overall survey-weighted probability in the population level.Results:The propensity score method has balanced the distributions of all observable covariates and has removed most of the selection bias among drug coverage groups.Our results indicate that Canadians with chronic conditions who are enrolled in a private benefits plan are more likely to use the associated medication.