Term of Award

Spring 2016

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.


Jiann-Ping Hsu College of Public Health

Committee Chair

Hani Samawi

Committee Member 1

Robert Vogel

Committee Member 2

Daniel Linder

Committee Member 3

Haresh Rochani

Committee Member 3 Email



In many studies, the measurement of sampling units according to the response variable is costly or time consuming, however, it is possible to rank sampling units according to baseline auxiliary covariates, which are available, easily obtainable, and cost efficient. In these cases, when estimating the population mean, Ranked Set Sampling (RSS) can be a more efficient sampling method than the Simple Random Sampling (SRS) method. In this dissertation, we propose a modified approach of the RSS method to allocate units into an experimental study, aimed to compare two or more groups.

Ranked auxiliary covariates, which are typically correlated with the variable of interest, are involved in sampling design; these covariates are available and affordable. Computer simulation is used to estimate the empirical nominal values and the empirical power values for the modified RSS, by using the regression approach in analysis of covariance (ANCOVA) models, and compared to the SRS. Results indicate that the required sample sizes for a given precision are smaller under RSS than under SRS.

The modified RSS protocol was applied to an experimental study conducted by the Department of Psychology, in collaboration with the College of Public Health, Department of Biostatistics, at Georgia Southern University. The experimental study was designed to obtain a better understanding of the pathways by which positive experiences (i.e., goal completion) contribute to higher levels of happiness, well-being, and life satisfaction. Using the RSS method resulted in significant cost reduction associated with smaller sample size without losing the significant precision of the analysis.