Electricity prices are characterised by strong autoregressive persistence, periodicity (e.g.intraday, day-of-the week and month-of-the-year effects), large spikes or jumps, GARCH and-as evidenced by recent findings- periodic volatility. We propose a multivariate model ofvolatility that decomposes volatility multiplicatively into a non-stationary (e.g. periodic) partand a stationary part with log-GARCH dynamics. Since the model belongs to the log-GARCHclass, the model is robust to spikes or jumps, allows for a rich variety of volatility dynamicswithout restrictive positivity constraints, can be estimated equation-by-equation by means ofstandard methods even in the presence of feedback, and allows for Dynamic ConditionalCorrelations (DCCs) that can –optionally- be estimated subsequent to the volatilities. We usethe model to study the hourly day-ahead system prices at Nord Pool, and find extensiveevidence of periodic volatility and volatility feedback. We also find that volatility ischaracterised by (positive) leverage in half of the hours, and that a DCC model provides abetter fit of the conditional correlations than a Constant Conditional Correlation (CCC) model.
展开▼
