An Application of the Mediation Effect on Multivariate Survival Model with Time-Varying Covariates

• Activity Number: 350
• Type: Contributed
• Date/Time: Tuesday, August 6, 2013 : 10:30 AM to 12:20 PM
• Sponsor: Biometrics Section
• Author(s): Yii-Chieh Huang*+ and Karen J Coleman and Corinna Koebnick and Kristi Reynolds and Anny H Xiang and Mary Helen Black and Sami Alskaf
• Companies: Kaiser Permanente and Kaiser Permanente and Kaiser Permanente and Kaiser Permanente and Kaiser Permanente and Kaiser Permanente and Kaiser Permanente
• Keywords: survival ; indirect effect ; mediation

Abstract

An important goal of the research is to analyze the causal mechanisms. Mediation analysis is the common one used to identify the indirect effect between the predictors and outcome. In the present study, we assess the characteristics associated with the metabolic syndrome and the impact of bariatric surgery on the resolution using KPSC Bariatric Surgery Registry. Bariatric surgery has become one of the most and long-lasting effective treatments for morbid obesity. This talk will focus on the resolution of the metabolic syndrome and discuss the issues of time-varying covariates in this multivariate survival setting. The effect of the mediator will also be evaluated to address the total effect of the outcome.