Date on Master's Thesis/Doctoral Dissertation
Bioinformatics and Biostatistics
Committee Co-Chair (if applicable)
Kulasekera, K.B. (Co-Chair)
This dissertation consists of two interconnected research projects. The first project was a study of propensity scores based statistical methods for estimating the average treatment effect (ATE) and the average treatment effect among treated (ATT) when there are two treatment groups. The ATE is defined as the mean of the individual causal effects in the whole population, while ATT is defined as the treatment effect for the treated population. Propensity score based statistical methods, such as matching, regression, stratification, inverse probability weighting (IPW), and doubly robust (DR) methods were used to estimate the ATE and ATT. Simulation studies and case studies were conducted to examine the performances of propensity score based methods when propensity score was estimated using logistic regression and generalized boosted models (GBM). The aim of the second project is to develop generalized propensity score based statistical methods for estimating ATE when there are more than two treatment groups. The generalized propensity score was estimated using multinomial logistic regression, random forests, and GBM. In addition, an adaptive optimal ensemble method was developed to estimate the generalized propensity score. Once the generalized propensity scores were obtained, IPW, stratification, and DR methods were used to estimate the ATE. Simulation studies were conducted to examine the performances of these different generalized propensity score based methods. In addition, we applied these methods to examine the outpatients health care costs under different treatments for patients with spinal fusion.
Abdia, Younathan, "Propensity score based methods for estimating the treatment effects based on observational studies." (2016). Electronic Theses and Dissertations. Paper 2504.