Measles outbreak detection in Metro Manila: Comparisons between ARIMA and INAR models

Date of Publication

2015

Document Type

Bachelor's Thesis

Degree Name

Bachelor of Science in Mathematics

Subject Categories

Mathematics

College

College of Science

Department/Unit

Mathematics and Statistics

Abstract/Summary

It has been the goal of many developing countries to stop the spread of diseases. Part of this effort is in conducting constant surveillance of disease transmission in order to foresee future epidemics. However, in the Philippine setting, there is a lack of an automated method in determining their presence. This paper presents a comparison between an integer-valued autoregressive model and the more commonly known autoregressive integrated moving average models in detecting the presence of disease outbreaks. Daily measles reports spanning from January 1, 2010 to January 14, 2015 was obtained from the Department of Health and was used as the original dataset for this study. Synthetic datasets were then generated using a modified Serfling model and conducting similarity tests using a dynamic time warping algorithm to ensure that simulated datasets observe similar behavior with the original set. False positive rates, sensitivity rates, and delay in detection are then evaluated between the two models. The results gathered show that an INAR model performs favorably compared to an ARIMA model, posting higher sensitivity rates, similar lag times, and equivalent false positive rates for three-day signal events.

Abstract Format

html

Language

English

Format

Electronic

Accession Number

CDTU021094

Shelf Location

Archives, The Learning Commons, 12F, Henry Sy Sr. Hall

Keywords

Measles--Philippines--Metro Manila; Algorithms

This document is currently not available here.

Share

COinS