search for




 

Analysis of accidents in domestic nuclear power plants using time series models
Journal of the Korean Data & Information Science Society 2019;30:119-26
Published online January 31, 2019;  https://doi.org/10.7465/jkdi.2019.30.1.119
© 2019 Korean Data and Information Science Society.

Jiwon Kang1 · Minho Kang2

1Department of Computer Science and Statistics, Jeju National University
2Korea Institute of Nuclear Nonproliferation and Control
Correspondence to: Researcher, Korea Institute of Nuclear Nonproliferation and Control, Daejeon 34054, Korea. E-mail: mhkang@kinac.re.kr
Received December 31, 2018; Revised January 11, 2019; Accepted January 11, 2019.
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
In this paper, we analyze the accidents data in domestic nuclear power plants from May 1978 to January 2018 based on the integer-valued time series models and perform the test for detecting the parameter change. Since there is some overdispersion in the data, we fit INGARCH model which reflects this property. After fitting the model, we employ the cumulative sum test based on the MLE to test whether the parameter change exists. As a result, the location of the significant change is October 2007. Additionally, the INGARCH model considering the parameter change is more appropriate than the INGARCH model without considering the parameter change in terms of the mean squared error or mean absolute error.
Keywords : Accidents in domestic nuclear power plants, integer-valued time series models, parameter change test.