Journal of Modern Mathematics and Statistics
ISSN: OnlineISSN: Print 1994-5388
Abstract
The Box-Jenkins Model building approach is used to fit a statistical time series model to the chemical viscosity reading data. The data were extracted from Box-Jenkins in called series D. The Normalized BIC was explored to compare the fitted ARIMA (1, 1, 1) Model with both the AR (1) and IMA (1, 1) Models fitted originally to the same series by Box-Jenkins in 1976. Among this class of significantly adequate set of ARIMA (p, d, q) Models of the same data set, the ARIMA (1, 1, 1) Model was found as the most suitable model with least BIC value of -2.366, MAPE of 2.424, RMSE of 0.301 and R2 of 0.749. Estimation by Ljung-Box test with Q (18) = 9.746, 16 d.f and p-value of 0.880 showed no autocorrelation between residuals at different lag times. Finally, a forecast for a lead time (l) of 12 was made.
How to cite this article:
E.P. Clement. Using Normalized BIC to Improve Box-Jenkins Model Building.
DOI: https://doi.org/10.36478/jmmstat.2013.1.7
URL: https://www.makhillpublications.co/view-article/1994-5388/jmmstat.2013.1.7