Detecting Change Signs with Differential MDL Change Statistics for COVID-19 Pandemic Analysis

Abstract

We are concerned with the issue of detecting changes and their signs from a data stream. For example, when given time series of COVID-19 cases in a region, we may raise early warning signals of outbreaks by detecting signs of changes in the cases. We propose a novel methodology to address this issue. The key idea is to employ a new information-theoretic notion, which we call the differential minimum description length change statistics (D-MDL), for measuring the scores of change sign. We first give a fundamental theory for D-MDL. We then demonstrate its effectiveness using synthetic datasets. We apply it to detecting early warning signals of the COVID-19 epidemic. We empirically demonstrate that D-MDL is able to raise early warning signals of events such as significant increase/decrease of cases. Remarkably, for about $64\%$ of the events of significant increase of cases in 37 studied countries, our method can detect warning signals as early as nearly six days on average before the events, buying considerably long time for making responses. We further relate the warning signals to the basic reproduction number $R0$ and the timing of social distancing. The results showed that our method can effectively monitor the dynamics of $R0$, and confirmed the effectiveness of social distancing at containing the epidemic in a region. We conclude that our method is a promising approach to the pandemic analysis from a data science viewpoint. The software for the experiments is available at https://github.com/IbarakikenYukishi/differential-mdl-change-statistics. An online detection system is available at https://ibarakikenyukishi.github.io/d-mdl-html/index.html