Fractional integration models for Italian electricity zonal prices Angelica Gianfreda and Luigi Grossi Abstract In the last few years we have observed an increasing interest in dereg- ulated electricity markets. Only few papers, to the authors’ knowledge, have con- sidered the Italian Electricity Spot market since it has been deregulated recently. This contribution is an investigation with emphasis on price dynamics accounting for technologies, market concentration and congestions as well as extreme spiky behavior. We aim to understand how technologies, concentration and congestions affect the zonal prices since these ones combine to bring about the single national price (prezzo unico d’acquisto, PUN). Implementing Reg–ARFIMA–GARCH mod- els, we draw policy indications based on the empirical evidence that technologies, concentration and congestions do affect Italian electricity prices. Key words: Congestions, Electricity Prices, Long Memory, Market power, Statis- tical analysis of financial data 1 Introduction and literature review Electricity prices display interesting features at daily level: mean–reversion, sea- sonality, time varying and clustered volatility, inverse leverage effect and extreme values called spikes or jumps, see for instance [9] and [5] among others. Earlier contributions proposed several specifications for the electricity price pro- cess, taking into account traded volume, price volatility, demand and margin as in [8] and again power consumption and water supply as in [9]. Hence we have found precedents, but none of these has been employed in the first empirical investiga- tions on the Italian market, see [2]. Following [7], we propose to consider possible congestions among zones, where a congestion is identified every time we observed different zonal prices. The technical factors underlying transmission network con- University of Verona, Department of Economics, Via dell’artigliere, 19, 37129 Verona e-mail: angelica.gianfreda@univr.it and luigi.grossi@univr.it 1