Premium
Advances in Box‐Jenkins modeling: 2. Applications
Author(s) -
McLeod Angus Ian,
Hipel Keith William,
Lennox William C.
Publication year - 1977
Publication title -
water resources research
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.863
H-Index - 217
eISSN - 1944-7973
pISSN - 0043-1397
DOI - 10.1029/wr013i003p00577
Subject(s) - box–jenkins , series (stratigraphy) , computer science , identification (biology) , transformation (genetics) , nonlinear system , system identification , time series , data mining , econometrics , industrial engineering , machine learning , autoregressive integrated moving average , engineering , mathematics , geology , paleontology , biochemistry , chemistry , botany , physics , quantum mechanics , gene , biology , measure (data warehouse)
Recent Box‐Jenkins techniques are employed to determine both nonseasonal and seasonal models for actual time series. The applied examples are carefully explained in order to demonstrate the utility of the new procedures that have been developed for use at the identification, estimation, and diagnostic check stages of model development. Even though more methods are now available for model building, it is demonstrated that this fact enhances rather than complicates the model construction phases. Furthermore, for all three applications considered, better models are obtained than it was previously possible to obtain. A new technique is described for optimal forecasting of the original time series when the data have been transformed by a nonlinear transformation.