search for




 

Forecasting the number of daily deaths using a lagged regression model
Journal of the Korean Data & Information Science Society 2021;32:1085-119
Published online September 30, 2021;  https://doi.org/10.7465/jkdi.2021.32.5.1085
© 2021 Korean Data and Information Science Society.

Changhui Choi1 · Yongwoon Cho2

12Korea Insurance Research Institute
Correspondence to: 1 Research fellow, Korea Insurance Research Institute, Seoul 07328, Korea.
2 Corresponding author: Research fellow, Korea Insurance Research Institute, Seoul 07328, Korea.
E-mail: ywcho@kiri.or.kr
Received July 23, 2021; Revised August 4, 2021; Accepted August 8, 2021.
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
Abstract
This research proposes a lagged regression model that predicts the number of daily deaths for certain male and female age groups. The entire dataset of death cases between 1997 and 2018 (5 million 6,700 thousand cases) and KMA (Korea Meteorological Administration) weather data of the matching period were used in constructing statistical models. According to the test results, deaths of males over 60 years old and females over 70 years old are particularly sensitive daliy temperature changes. When fitted to data of 1997 and 2017, the proposed model were able to predict the number of daily deaths with 10% average accuracies for males over 60 years old and females over 70, and 5.4% accuracy for the entire population.
Keywords : Cause-of-death data, cluster analysis, lagged-regression, weather data.