Logo
Munich Personal RePEc Archive

An Error Correction Model for Forecasting Philippine Aggregate Electricity Consumption

Danao, Rolando and Ducanes, Geoffrey (2016): An Error Correction Model for Forecasting Philippine Aggregate Electricity Consumption. Forthcoming in: Electricity Policy in the Philippines: Generation, Institutions, and Prices No. Stand-alone book to be published by the University of the Philippine Press (2019)

[thumbnail of MPRA_paper_87722.pdf]
Preview
PDF
MPRA_paper_87722.pdf

Download (558kB) | Preview

Abstract

This paper presents an error correction model for forecasting electricity consumption in the Philippines based on income, price, and temperature. The empirical evidence shows that there is a long-run positive and inelastic relationship between electricity consumption and income. We find that income, price, and temperature have significant short-run effects. Short-run demand is positive and inelastic with respect to income, negative and inelastic with respect to price, and positive and elastic with respect to temperature. Despite the small sample size, the model passes the standard diagnostic and parameter stability tests and performs well in within-sample and out-of-sample forecasting. It can be used not only for forecasting but also for analyzing, through simulations, the impacts on electricity consumption of changes in income, price, and temperature.

The simulations confirm that, in the long run, electricity consumption is mainly driven by economic growth. Increasing GDP growth rate from 6% per year to 7% could increase electricity consumption at the end of 15 years by 10%. Although the effect of electricity price on electricity consumption is small (because of low price elasticity in absolute terms) and the effect of temperature change is also small (because annual average temperature change is small), their combined effects could add up and our simulation indicates that under very conservative assumptions, electricity consumption at the end of 15 years could rise further by 2%. Thus, it is important to include these variables in the simulations in order to account for their combined effects.

Atom RSS 1.0 RSS 2.0

Contact us: mpra@ub.uni-muenchen.de

This repository has been built using EPrints software.

MPRA is a RePEc service hosted by Logo of the University Library LMU Munich.