PERAMALAN JUMLAH KASUS COVID-19 DI SEMARANG MENGGUNAKAN METODE AUTOREGRESSIVE INTEGRATED MOVING AVERAGE

Abstract

The ARIMA (Autoregressive Integrated Moving Average) method is a forecasting
method developed by George Box and Gwilym Jenkins which is often called the
Box-Jenkins time series method.The ARIMA model is a combined model of the
Autoregressive (AR) and Moving Average (MA) models. ARIMA is written with
the ARIMA notation (p, d, q), where p states the order of the AR process, the d
statement of order from difference is made so that the data is stationary, and q is
the order statement from the MA process. To get the ARIMA model it is done with
three The modeling strategy stage is Identification, Assessment, and Testing
(Pankratz, 1991). This paper describes the ARIMA model of positive patients and
recovered patients in the city of Semarang. The data observed are daily data from
9 April 2020 to 7 August 2020 as many as 121 data The results of the time series
analysis show that for positive patients the ARIMA model (2,1,8) is obtained and
the patients who recover are obtained the ARIMA model (2,1,10). sis showed that
the AIC values in the patients were positive and the patients recovered were
456.66 and 338.41, respectively. Predictions of covid-19 patients for the next 30
periods for positive patients and patients recovering In the following days there
will be fluctuations in positive covid-19 patients, this pandemic case can also
change at any time depending on the efforts of the Semarang city government and
also public awareness to always maintain hygiene and also implement health
protocols that have been put in place to reduce the chain of viruses.

Keywords: ARIMA, MA, AR, AIC, Box-Jenkins