A1042
Title: Change point detection through copula-based Markov models
Authors: Li-Hsien Sun - National Central University (Taiwan) [presenting]
Ming-Hua Hsieh - National Chengchi University (Taiwan)
Dong-Hua Kuo - National Central University (Taiwan)
Abstract: Time series analysis is critical in various fields such as finance, industry, and biology. However, due to the possibility of the structure change, problems, such as loss or damage, can be expected (e.g., the stock market during the financial crisis in 2008 and COVID-19 in 2020). Hence, the corresponding change point for structural change is worth studying. In order to detect the changepoint online for time series data or correlated data, the model is proposed for online changepoint detection via copula-based Markov models where the time serial data is described by copula-based Markov model and the change-point detection based on the run length distribution using the Bayesian approach. Finally, the performance of the proposed method is illustrated through numerical and empirical studies.