Page 365 - Proceeding The 2nd International Seminar of Science and Technology : Accelerating Sustainable Innovation Towards Society 5.0

he 2 International Seminar of Science and Technology
nd
“Accelerating Sustainable innovation towards Society 5.0”
ISST 2022 FST UT 2022
Universitas Terbuka

3) Identify the model to get the best model with the smallest error
value.
4) Evaluating the best model and forecasting the central oxygen
supply using the best model with the smallest error value.
1.2 Decomposition
According to Makkulau [3] the decomposition method is a method that
uses four main components in predicting future values. The four
components include trend, seasonality, cycle, and error. The
decomposition method is based on the assumption that the existing
data is a combination of several components, which is simply
described as Equation (1) [13].
Data = Pattern + error (1)
= f (trend, cycle, seasonal) +error
The assumption above means that there are four components that
affect a time series, namely three components that can be identified
due to certain patterns, including trends, cycles and seasonality. The
general mathematical equation of the decomposition approach is in
Equation (2), where Xt = time series value (actual data) in period, Tt =
trend component in period t, St = seasonal component in period t, Ct
= cyclical component in period t, It = component of irregular error in
period t, t = period (time).
Xt = f (Tt, St, Ct, It) (2)

The research stages are generally described in the flow chart as
follows:
1) The first step in the Decomposition analysis is to input data into the
Minitab software.
2) Start the analysis by selecting the Stat tools, then select Time
Series, then select decomposition.
3) Then input the name of the data variable to be analyzed and fill in
the Generate Forecasts with how long the forecasting will take,
then click Ok.

328 ISST 2022 – FST Universitas Terbuka, Indonesia
International Seminar of Science and Technology “Accelerating Sustainable
Towards Society 5.0