Term of Award

Fall 2020

Degree Name

Doctor of Public Health in Biostatistics (Dr.P.H.)

Document Type and Release Option

Dissertation (open access)

Copyright Statement / License for Reuse

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.

Department

Department of Biostatistics, Epidemiology, and Environmental Health Sciences

Committee Chair

Hani Samawi

Committee Member 1

Haresh Rochani

Committee Member 2

Lili Yu

Abstract

Modern research strategies rely predominantly on three steps, data collection, data analysis, and inference. In research, if the data is not collected as designed, researchers may face challenges of having incomplete data, especially when it is non-ignorable. These situations affect the subsequent steps of evaluation and make them difficult to perform. Inference with incomplete data is a challenging task in data analysis and clinical trials when missing data related to the condition under the study. Moreover, results obtained from incomplete data are prone to biases. Parameter estimation with non-ignorable missing data is even more challenging to handle and extract useful information. This dissertation proposes a method based on the influential tilting resampling approach to address non-ignorable missing data in statistical inference. This robust approach is motivated by a brief use of the importance resampling approach used by Samawi et al. (1998) for power estimation. The exponential tilting also inspires it for non-ignorable missing data proposed by Kim & Yu (2011). One of the proposed approach bases is assuming that the non-respondents' model corresponds to an exponential tilting of the respondents' model. The tilted model's specified function is the influential function of the function of interest (parameter). The other bases of the proposed approach are to use the importance resampling techniques to draw inference about some model parameters. Extensive simulation studies were conducted to investigate the performance of the proposed methods. We provided the theoretical justification, as well as application to real data.

OCLC Number

1233791318

Research Data and Supplementary Material

No

Share

COinS