Date of Award

Spring 2026

Language

English

Embargo Period

5-1-2026

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

Second Advisor

Igor Zurbenko

Committee Members

Edward Valachovic, Eric Rose

Keywords

Spectral, Traffic, Fourier, KZFT, Signal Analysis

Subject Categories

Applied Statistics | Biostatistics | Data Science | Longitudinal Data Analysis and Time Series | Other Oceanography and Atmospheric Sciences and Meteorology | Other Physical Sciences and Mathematics

Abstract

In this paper we estimate the spectral density of traffic accident events in the Capital Distict, NY area using a band-pass filter known as the Kolmogorov-Zurbenko Fourier Transform (KZFT). The source data is provided by Moosavi, et al. (2019) and originally captured from various public entities and sensors in the road network. Spectral density estimation with KZFT suppresses noise to reveal the constituent frequencies embedded in the noisy signal. Signal reconstruction based on KZFT produces an approximate weekly accident arrivals for this noisy signal, or in other words a pattern which is proportionate to the event expectation viewed over a calendar week. The weekly pattern restated on a relative incidence basis is used to forecast the aggregate weekly pattern of 2021 also on a relative incidence basis. The weekly pattern produced by KZFT performs favorably against a null model with RMSE reduction of 44%. KZFT and spectral analysis methods in general have typically been applied to signals which are highly determined by physical forces - objects that spin, oscillate, vibrate, orbit, and so forth. Our novel application of these methods to highly random traffic accident events governed largely by population travel patterns and not by any fundamental physical processes demonstrates their potential for broader adoption among researchers working with signals in varied domains.

License

Creative Commons Attribution 4.0 International License
This work is licensed under a Creative Commons Attribution 4.0 International License.

Download

Share

COinS