Bayesian approach on short time-course data of protein phosphorylation, casual inference for ordinal outcome and causal analysis of dietary and physical activity in T2DM using NHANES data.

bayesian;protein phosphorylation;causal inference;ordinal outcome;path analysis;T2DM

You Wu

University:University of Louisville

Department:Bioinformatics and Biostatistics

关键词: bayesian;    protein phosphorylation;    causal inference;    ordinal outcome;    path analysis;    T2DM;   

Others  :  https://ir.library.louisville.edu/cgi/viewcontent.cgi?article=3929&context=etd

美国|英语

来源: The Universite of Louisville's Institutional Repository

【 摘 要 】

This dissertation contains three different projects in proteomics and causal inferences. In the first project, I apply a Bayesian hierarchical model to assess the stability of phosphorylated proteins under short-time cold ischemia. This study provides inference on the stability of these phosphorylated proteins, which is valuable when using these proteins as biomarkers for a disease. in the second project, I perform a comparative study of different confounding-adjusted to estimate the treatment effect when the outcome variable is ordinal using observational data. The adjusted U-statistics method is compared with other methods such as ordinal logistic regression, propensity score based stratification and matching. In the third project, I perform a causal analysis of the combination of dietary information and physical activity in type 2 diabetes across different ethnic groups: White, African American and Mexican American. Such information may contribute to a better understanding of type 2 diabetes variation between ethnic groups, and a better understanding of type 2 diabetes among different ethnic groups and between female and male.