Premium
Space‐Time Model versus VAR Model: Forecasting Electricity demand in Japan
Author(s) -
Ohtsuka Yoshihiro,
Kakamu Kazuhiko
Publication year - 2013
Publication title -
journal of forecasting
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.543
H-Index - 59
eISSN - 1099-131X
pISSN - 0277-6693
DOI - 10.1002/for.1255
Subject(s) - autoregressive model , econometrics , electricity demand , autoregressive–moving average model , vector autoregression , autoregressive integrated moving average , bayesian vector autoregression , bayesian probability , state space representation , dependency (uml) , time series , economics , computer science , statistics , mathematics , electricity generation , power (physics) , artificial intelligence , physics , quantum mechanics , algorithm
This paper examined the forecasting performance of disaggregated data with spatial dependency and applied it to forecasting electricity demand in Japan. We compared the performance of the spatial autoregressive ARMA (SAR‐ARMA) model with that of the vector autoregressive (VAR) model from a Bayesian perspective. With regard to the log marginal likelihood and log predictive density, the VAR(1) model performed better than the SAR‐ARMA( 1,1) model. In the case of electricity demand in Japan, we can conclude that the VAR model with contemporaneous aggregation had better forecasting performance than the SAR‐ARMA model. Copyright © 2011 John Wiley & Sons, Ltd.