Theses and Dissertations

Date of Award

8-1-2024

Document Type

Thesis

Degree Name

Master of Science (MS)

Department

Mathematics

First Advisor

Tamer Oraby

Second Advisor

Michael Machiorlatti

Third Advisor

Hansapani Rodrigo

Abstract

In the repeated measures longitudinal datasets where missing data is a relatively common issue, we explored different imputation methods, including machine learning (ML) methods in order to examine potential efficiencies for using traditional versus newer computational methods. In order to accomplish said comparison, we used a Monte Carlo simulation experiment of a population of size N=70000 to mimic a clinical trial, with different scenarios of missing at random (MAR) data in the response variable. To compare the behavior of each method resulting from the difference between population and sample dataset, a real dataset was used from the Boston College on "National Longitudinal Survey" to simulate MAR. Moreover, we used both datasets to examine the effects of different sample sizes when using Bayesian neural networks and k-Nearest Neighbors (k-NN) for imputations and compared that to the more traditional methods of last observed carried forward, multiple imputation, and linear regression. Additionally, the cost of computing power is evaluated at different sample sizes for each scenario on both datasets.

Comments

Copyright 2024 Joseph O. Alanis. https://proquest.com/docview/3116494195

Download

Included in

Mathematics Commons

Share

COinS