The demand for electricity in Israel

Quarterly data for Israel are used to compare and contrast three dynamic ec onometric methodologies for estimating the demand for electricity by househ olds and industrial companies. These are the Dynamic Regression Model and t wo approaches to cointegration (OLS and Maximum Likelihood). Since we find evidence of seasonal unit roots in the data we also test for seasonal coint egration. We find that the scale elasticities are similar in all three appr oaches but the OLS price elasticities are considerably lower. Moreover, OLS suggests non-cointegration. The paper concludes by stochastically simulati ng the DRMs to calculate upside-risk in electricity demand. (C) 1999 Elsevi er Science B.V. All rights reserved. JEL classifications: Q41.