A non-central beta model to forecast and evaluate pandemics time series

摘要: Government, researchers, and health professionals have been challenged to model, forecast, evaluate pandemics time series (e.g. new coronavirus SARS-CoV-2, COVID-19). The main difficulty is the level of novelty imposed by these phenomena. Information from previous epidemics only partially relevant. Further, spread local-dependent, reflecting a number social, political, economic, environmental dynamic factors. present paper aims provide relatively simple way incidence pandemic. proposed framework makes use non-central beta (NCB) probability density function. Specifically, probabilistic optimisation algorithm searches for best NCB model pandemic, according mean square error metric. resulting allows one infer, among others, general peak date, ending total cases as well compare difficult pandemic territories. Case studies involving COVID-19 countries around world suggest usefulness in comparison with some epidemic models literature SIR, SIS, SEIR) established formalisms exponential smoothing - ETS, autoregressive integrated moving average ARIMA).