Running head: BOX-JENKINS METHODOLOGY
BOX-JENKINS METHODOLOGY 2
Box –Jenkins Methodology
The Box –Jenkins is a method that uses mathematical concepts to identify and predict data from a given time sequence. The method uses the autoregressive integrated moving average (ARIMA) and checking the season’s differences to generate a forecast of the future points in a given series. The method is applicable in the circumstances when the given data requires a time series of observation for both short and long periods of time (Gairaa et al., 2016). The model works based on the three principles such as autoregressive, differentiating and moving averages commonly donated as p,d,q which are automated in the model to give the best fitting points in a given data and then the outcome is determined from there differences.
The model is valuable in circumstances where given data to be forecasted in time serious requires making several observations to make a general prediction of the outcome points. For example, the method can be used in the chemical process to predict the chemical concentration for a given set of data that normally requires a long period of time and several observations (Sufahani et al., 2017). The Box-Jenkins model that involves identification of data point at fixed time intervals helps in the accuracy of the predicted points.the objective of the model in the identification of the data points is to determine the seasonality of different points for easy forecasting.
Seasonality in the Box –Jenkins model is useful in that identifying the occurrence of various data points at different time intervals. The intervals may be in the form of selected minutes, hours days or even weeks depending on the data are given and time sequence allocate for the prediction process (Jackson, Sillah & Tamuke, 2018). Seasonality in the model helps in eliminations components or points that display seasonal interval for the given data. This eases the analyzation process basing on the trend taken from the fitting points through aggressions and predicts the data.
Gairaa, K., Khellaf, A., Messlem, Y., & Chellali, F. (2016). Estimation of the daily global solar radiation based on Box–Jenkins and ANN models: a combined approach. Renewable and Sustainable Energy Reviews, 57, 238-249.
Jackson, E. A., Sillah, A., & Tamuke, E. (2018). Modelling monthly headline consumer price index (HCPI) through seasonal Box-Jenkins methodology. International Journal of sciences, 7(01), 51-56.
Sufahani, S., Che-Him, N., Khamis, A., Rusiman, M. S., Arbin, N., Yee, C. K. … & Azmi, Z. A. (2017). Descriptive Statistics with Box-Jenkins and Marketing Research for Jewellery Company in Malaysia. Far East Journal of Mathematical Sciences, 101(10), 2151-2161.