Open AccessPeramalan dan deteksi outlier saham perusahaan angkutan laut umum di masa covid-19 dengan pemodelan arima
Author(s) -
Ilham Thaib,
Gesit Thabrani,
Silvia Netsyah
Publication year - 2021
Publication title -
jurnal kajian manajemen dan wirausaha
Language(s) - English
Resource type - Journals
ISSN - 2655-6499
DOI - 10.24036/jkmw02114850
Subject(s) - autoregressive integrated moving average , partial autocorrelation function , outlier , econometrics , statistics , box–jenkins , autocorrelation , statistical hypothesis testing , stock (firearms) , mathematics , time series , geography , archaeology
The public sea freight sector is one of the affected by COVID-19. PT. Samudera Indonesia Tbk is one of the sea transportations companies in Indonesia. The ARIMA model in the previous study provided a statistical test with the aim of evaluating the suitability of the model with a p value of less than 0.05 to determine ARIMA by guessing through ACF (Autocorrelation Function) and PACF (Partial Autocorrelation Function) through stationary data. Outlier detection can be done by plotting the residuals from the specified model. Forecasting data for the next 5 days using the ARIMA (3,1,2) model can be seen that the results of forecasting stock price data for PT. Samudera Indonesia Tbk using ARIMA (3,1,2) is within the 95% confidence interval with a forecast value that is close to the actual value. There are outliers that are detected which are related to economic phenomena.Keywords: Forecasting, Covid-19, stock, ARIMA, outlier