Author ORCID Identifier
Date of Award
8-7-2024
Degree Type
Thesis
Degree Name
Master of Science (MS)
Department
Mathematics and Statistics
First Advisor
Yichuan Zhao
Second Advisor
Jing Zhang
Third Advisor
Li-Hsiang Lin
Abstract
The thesis aims to determine, independent of sample size, a quick and effective way to test the equality of several samples without making any assumptions about their distribution. For example, we could use a k-sample test to compare the efficacy of various vaccines and see if they are equally effective. We created a new test by combining empirical likelihood methods with the ’divide and conquer’ strategy. Ninety-five percent of the time, our test correctly identified samples from the same distribution, and eighty percent of the time, samples from different distributions. It is similar to other tests but completed in a fraction of the time needed by current methods, producing results much faster
DOI
https://doi.org/10.57709/37442086
Recommended Citation
Tella, Jeremiah Adetunji, "Scalable K-Sample Test via Divide and Conquer & Empirical Likelihood Method." Thesis, Georgia State University, 2024.
doi: https://doi.org/10.57709/37442086
File Upload Confirmation
1