An interesting feature of some electricity logprice series is that they display daytime upward spikes and nighttime downward spikes. This paper will show that this phenomenology implies that the underlying data generating mechanism involves an implicit threshold behavior, and consequently that threshold stochastic dynamic models can be well suited to study this kind of series. As a worked out example, a specific four-threshold TARX model will be applied to AESO power market data.
Spikes, antispikes and thresholds in electricity logprices 2013 10th International Conference on the European Energy Market (EEM)
LUCHERONI, Carlo
2013-01-01
Abstract
An interesting feature of some electricity logprice series is that they display daytime upward spikes and nighttime downward spikes. This paper will show that this phenomenology implies that the underlying data generating mechanism involves an implicit threshold behavior, and consequently that threshold stochastic dynamic models can be well suited to study this kind of series. As a worked out example, a specific four-threshold TARX model will be applied to AESO power market data.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
