Generalized spatiotemporal modeling and causal inference for assessing treatment effects for multiple groups for ordinal outcome.
Date on Master's Thesis/Doctoral Dissertation
Bioinformatics and Biostatistics
Committee Co-Chair (if applicable)
Hierarchical hurdle model; health professional shortage; superiority score; ordinal outcome; antibiotic overuse; generalized spatiotemporal model
This dissertation consists of three projects and can be categorized in two broad research areas: generalized spatiotemporal modeling and causal inference based on observational data. In the first project, I introduce a Bayesian hierarchical mixed effect hurdle model with a nested random effect structure to model the count for primary care providers and understand their spatial and temporal variation. This study further enables us to identify the health professional shortage areas and the possible impacting factors. In the second project, I have unified popular parametric and nonparametric propensity score-based methods to assess the treatment effect of multiple groups for ordinal outcome. I have conducted different simulation scenarios and compared the performance of those methods. In the third project, I have introduced a generalized spatiotemporal model to identify the antibiotic medication overuse in Kentucky. In this project, I used the Medicaid data to understand the spatial and seasonal variation of the antibiotic overuse for children insured by Kentucky Medicaid.
Ghosal, Soutik, "Generalized spatiotemporal modeling and causal inference for assessing treatment effects for multiple groups for ordinal outcome." (2018). Electronic Theses and Dissertations. Paper 3039.
Biostatistics Commons, Health Services Administration Commons, Health Services Research Commons, Statistical Methodology Commons, Statistical Models Commons