Degree Name

MS (Master of Science)

Program

Mathematical Sciences

Date of Award

12-2025

Committee Chair or Co-Chairs

Mostafa Zahed

Committee Members

Jeff Knisley, Maryam Skafyan

Abstract

Lung and colon cancers are among the leading causes of cancer-related mortality worldwide, with significant variations across different healthcare systems. This study applies multivariate time series modeling and forecasting to analyze lung and colon cancer mortality trends in Jamaica and the United States, examining each cancer type separately within each country and comparing trends between the two regions. The research employs multivariate time series models to assess the interdependence between lung and colon cancer mortality from 1960 to 2021 within Jamaica and the U.S. Multivariate forecasting will be performed separately for both countries to evaluate country-specific trends for 10 years beyond 2021. A comparative analysis will then be conducted to identify disparities, similarities, and potential factors influencing mortality differences between the two countries. Model selection and validation are conducted using statistical performance metrics such as Mean Absolute Percentage Error (MAPE), Root Mean Squared Error (RMSE), and Akaike Information Criterion (AIC) to ensure the most accurate forecasting models. To enhance predictive robustness, Monte Carlo simulation techniques generate probabilistic forecasts, accounting for variability in future mortality trends. This study provides data-driven insights into lung and colon cancer mortality trends in Jamaica and the U.S. By integrating multivariate forecasting and simulation approaches, this research contributes to the development of advanced statistical models for understanding and predicting cancer mortality, aiding in future public health planning and policy development.

Document Type

Thesis - embargo

Copyright

Copyright by the authors.

Download

Available for download on Friday, January 15, 2027

Share

COinS