Electronic Theses and Dissertations





Document Type


Degree Name

Master of Science


Mathematical Sciences



Committee Chair

Ebenezer O. George

Committee Member

Dale Bowman

Committee Member

Su Chen


In scientific investigations, it is common to have several studies that deal with a common theme or hypothesis. In many such studies, independent test statistics or their corresponding p-values are usually available. Since the conclusions of such studies are not always conclusive, combining these independent results can reinforce the individual results and lead to a conclusive statement about the common hypothesis in question. In recent times, such meta-analytic procedure is usually required in such as genomics studies where detection of statistical significance based on one study is hard to obtain due to the inadequate sample size required because of the large number of genes that are usually interrogated. Simple computer tools for implementing these combination of P-values are not commonly available to non-statistically sophisticated user. In this thesis, we develop an easily deployed and feasible package that allows for the independent combination of p-values in two highly utilized programming languages. Users will be able to easily apply one of the affirmed methodologies. Packages were created in both R and Python, deployed to both main repositories (i.e., CRAN and PyPi), and tested against existing p-value data sets from other packages available for accuracy. With the need for this functionality to be readily available in two of the major programming languages used in both statistics and data science, the feasibility and utility of this package is apparent.


Data is provided by the student.

Library Comment

Dissertation or thesis originally submitted to the local University of Memphis Electronic Theses & dissertation (ETD) Repository.