Sas enterprise version 9

Data were weighted to be representative of the US adult current and recent former commercial tobacco users. Sample characteristics (i.e., demographics, tobacco product use status) were summarized in weighted percentages. Prevalence estimates of awareness of HTPs and HTP use, as well as HTP-related beliefs overall and by sample characteristics, were calculated. Weighted logistic regression models were used to examine the association of demographics and tobacco product use status with HTP awareness, ever use, and current use. Specifically, the first set of models included only demographics, and the second set of models additionally included tobacco product use statuses. We employed this approach so that we did not dilute the association between demographics and HTP awareness and use since demographics can be causally related to HTP awareness and use through other tobacco product use. Finally, weighted multinomial logistic regression was conducted to examine the associations between HTP-related beliefs and HTP use statuses. Each belief was modeled separately, adjusting for demographics and tobacco product use statuses. Because beliefs did not differ significantly by the randomized images respondents saw, we did not include the image seen as a covariate in the model. All analyses were conducted in SAS^® Enterprise version 9.4 (SAS Institute, Inc.: Carey, NC, USA).

To account for the complexity of the CCHS survey design, ensure representative population estimates and account for survey non-response bias, Statistics Canada bootstrap survey weights were incorporated into the analysis using a pooled approach (Thomas and Wannell 2009 (link)). Approximately 83.6% of CCHS respondents were successfully linked to administrative data. Baseline descriptive statistics were calculated for HCUs (top 5%), non-HCUs (bottom 95%) and for the cohort overall. Logistic models were developed for 4-year trajectories among baseline non-HCUs to investigate associations between health behaviours according to unadjusted, age-sex-adjusted, age-sex-income adjusted and models adjusted for collapsed aggregated diagnostic groups (ADG)-age-sex and income. All analyses were conducted using SAS Enterprise version 9.4.