Adding Dummy Variables: A Simple Approach for Improved Volatility Forecasting in Electricity Market

Abstract

This paper uses dummy variables to measure day-of-the-week effects and structural breaks on volatility. Considering day-of-the-week effects, structural breaks, or both, we propose three classes of HAR models for forecasting electricity volatility based on the existing HAR models. The estimation results of the models show that day-of-the-week effects only improve the fitting ability of HAR models for forecasting electricity volatility at daily horizon, and structural breaks can improve the in-sample performance of HAR models when forecasting electricity volatilities at daily, weekly, and monthly horizons. The out-of-sample analysis indicates that both day-of-the-week effects and structural breaks contain additional ex ante information for predicting electricity volatility, and in most cases dummy variables for measuring structural breaks contain more out-of-sample predictive information than those for measuring day-of-the-week effects. The out-of-sample results are robust across three different ways. More importantly, we argue that adding dummy variables for measuring day-of-the-week effects and structural breaks can improve the performance of most of the other existing HAR models for forecasting volatility in electricity market.

Keywords: Day-of-the-week effects, Structural breaks, Volatility Forecasting, Realized volatility, Electricity market