Forecasting COVID-19 Epidemic in Spain and Italy Using A Generalized Richards Model with Quantified Uncertainty

Isnani Darti, Agus Suryanto, Hasan S. Panigoro, Hadi Susanto

Research output: Contribution to journalArticlepeer-review

12 Scopus citations

Abstract

The Richards model and its generalized version are deterministic models that are often implemented to fit and forecast the cumulative number of infective cases in an epidemic outbreak. In this paper we employ a generalized Richards model to predict the cumulative number of COVID-19 cases in Spain and Italy, based on available epidemiological data. To quantify uncertainty in the parameter estimation, we use a parametric bootstrapping approach to construct a 95% confidence interval estimation for the parameter model. Here we assume that the time series data follow a Poisson distribution. It is found that the 95% confidence interval of each parameter becomes narrow with the increasing number of data. All in all, the model predicts daily new cases of COVID-19 reasonably well during calibration periods. However, the model fails to produce good forecasts when the amount of data used for parameter estimations is not sufficient. Based on our parameter estimates, it is found that the early stages of COVID-19 epidemic, both in Spain and in Italy, followed an almost exponentially growth. The epidemic peak in Spain and Italy is respectively on 2 April 2020 and 28 March 2020. The final sizes of cumulative number of COVID-19 cases in Spain and Italy are forecasted to be at 293220 and 237010, respectively.

Original languageBritish English
Pages (from-to)90-100
Number of pages11
JournalCommunication in Biomathematical Sciences
Volume3
Issue number2
DOIs
StatePublished - 12 Jan 2020

Keywords

  • Boostraap
  • COVID-19
  • Generalized Richards Models
  • Uncertainty

Fingerprint

Dive into the research topics of 'Forecasting COVID-19 Epidemic in Spain and Italy Using A Generalized Richards Model with Quantified Uncertainty'. Together they form a unique fingerprint.

Cite this