Development of efficient simultaneous confidence bounds for linear mixed models with applications in alcohol research
Multiplicity corrections are necessary to ensure the accuracy of conclusions made in studies that carry out multiple inferences simultaneously. This thesis uses the methodology derived by Hunter and Worsley to obtain improved simultaneous confidence bounds (SCBs) that are less conservative than the highly used Bonferroni SCBs, for studies using linear mixed modeling. Empirical coverage rates were obtained for data that was generated using simulations, to compare the accuracy of the Hunter-Worsley SCBs with that of the Bonferroni SCBs. The bounds were also applied to data in the field of alcohol research, where comparisons were made to determine the moderating effect of post-traumatic stress disorder (PTSD) and suicidal tendencies on the efficacy of three brief alcohol interventions (BA: Brief Advice, BMI: Brief Motivational Intervention, BMI-B: BMI with a telephone booster session). No significant differences in coverage rates for the simulated data were observed between the Hunter-Worsley SCBs and the Bonferroni SCBs at lower correlation values, but an improvement was observed for the Hunter-Worsley SCBs over the Bonferroni SCBs at higher correlation values. In the analysis of the alcohol research data, a negative moderating effect for PTSD was observed on the efficacy of BMI for two of the alcohol outcomes. Additionally, a patient who contemplated suicide's suicidal tendency level negatively moderated the effect of BMI-B on one of the alcohol outcomes. No significant difference between the Hunter-Worsley SCBs and the Bonferroni SCBs was observed when generating bounds for the alcohol research data.
Sequeira, Emmanuel, "Development of efficient simultaneous confidence bounds for linear mixed models with applications in alcohol research" (2016). ETD Collection for University of Texas, El Paso. AAI10151193.