STL Decomposition and SARIMA Model: The Case for Estimating Value-at-Risk of Covid-19 Increment Rate in DKI Jakarta

Agnes Zahrani Agnes Zahrani,Siti Sa’adah Siti Sa’Adah,Aniq A Rohmawati Aniq A Rohmawati

doi:10.21108/ijoict.v7i2.553

Abstract

In this research, we propose an extreme values measure, the Value-at-Risk (VaR) based Seasonal Trend Loess (STL) Decomposition and Seasonal Autoregressive Integrated Moving Average (SARIMA) models, which is more sensitive to the seasonality of extreme value than the conventional VaR. We consider the problem of the seasonality and extreme value for increment rate of Covid-19 forecasting. For stakeholder, government and regulator, VaR estimation can be implemented to face the extreme wave of new positive Covid-19 in the future and minimize the losses that possibly affected in term of financial and human resources. Specifically, the estimation of VaR is developed with the difference lies on parameter estimators of STL and SARIMA model. The VaR has coverage probability as well as close 1-α. Thus, we propose to set α as parameter to estimate VaR. Consequently, the performance of VaR will depend not only on parameter model but also α. Our aim estimates VaR with minimum α based on correct VaR value. Numerical analysis is carried out to illustrate the estimative VaR.

Highlights

There is unpredictable how long the Covid-19 pandemic will discontinue
We provide training data to construct the Seasonal Trend Loess (STL)-Seasonal Autoregressive Integrated Moving Average (SARIMA) model, considering the Rainfall Forecasting research [18] which proved that the larger the training data, the better results obtained
Our state-of-the-art VaR method by using STL-SARIMA model as a support to estimate the data we use, compared to the previous research [4], VaR is used without any parameters of the model

Summary

Introduction

There is unpredictable how long the Covid-19 pandemic will discontinue. There are some important aspects that have been carried out from this pandemic, including the public’s efforts to slow spread and researchers’ work to observe more about the virus. From the beginning of the health crisis, following the news of the first and second positive case in Indonesia due to the Covid-19 on March 2, 2020, it has shocked the public. As the largest capital and metropolitan district of Indonesia, the province that has contributed the most to positive cases of Covid-19 in Indonesia is DKI Jakarta. This can be justified due to the fact that the mobility of the people in DKI Jakarta is relatively massive compared to 34 other provinces. The Indonesian government has taken a number of measures with hope of preventing the Covid-19 to massive spreading, one of which is by imposing large-scale social restrictions. Since the high volatility of daily increment rate of Covid-19 lately, estimating the extreme value of increment rate become a crucial matter to support information and maintain essential health services

Methods

Results

Conclusion