Date of Award
Spring 2026
Language
English
Embargo Period
4-24-2026
Document Type
Master's Thesis
Degree Name
Master of Science (MS)
College/School/Department
Department of Epidemiology and Biostatistics
Program
Biostatistics
First Advisor
Edward Valachovic
Committee Members
Eric J. Rose
Subject Categories
Biostatistics
Abstract
Alzheimer’s disease mortality has substantially risen in recent history, placing a significant burden on public health infrastructure and highlighting the need for improved analytical methods to better understand mortality data patterns and offer reliable predictions. Time series methods often struggle to balance both accuracy and interpretability, which hinders the ability to gather meaningful insights from time series data. To address these limitations, this study applies the Kolmogorov-Zurbenko (KZ) filter to monthly U.S. Alzheimer’s mortality data spanning from 1999 to 2023 and decomposes the series into long-term trend, seasonal, and noise components on a logarithmic scale. Long-term trend accounts for 86.49% total variability in the series, with an annual increase of 4.18% over the observation period. Seasonal patterns demonstrate consistent peaks in winter months, as well as evidence of slight seasonality shifts coinciding with the COVID-19 pandemic. Forecasting performance across four models, evaluated using a 90/10 train-test split, showed improvement upon a seasonal naïve benchmark when using the KZ-based approach (MAPE = 10.94% vs. 8.96%), but outperformance by ETS (MAPE = 4.51%), underscoring tradeoffs of a KZ approach in terms of predictive accuracy. An exploratory ensemble approach predicted a 5.6% mortality increase over a 5-year horizon while estimating a total of 663,382 deaths, providing a baseline to inform public health decisions pertaining to Alzheimer’s over the forecast horizon.
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Recommended Citation
Farrell, Jack D., "Time Series Decomposition and Forecasting of Alzheimer’s Disease Mortality Using a Kolmogorov-Zurbenko Filter" (2026). Electronic Theses & Dissertations (2024 - present). 394.
https://scholarsarchive.library.albany.edu/etd/394