Scaling analysis of multivariate intermittent time series
arXiv:cond-mat/0501325 · doi:10.1016/j.physa.2005.01.038
Abstract
The scaling properties of the time series of asset prices and trading volumes of stock markets are analysed. It is shown that similarly to the asset prices, the trading volume data obey multi-scaling length-distribution of low-variability periods. In the case of asset prices, such scaling behaviour can be used for risk forecasts: the probability of observing next day a large price movement is (super-universally) inversely proportional to the length of the ongoing low-variability period. Finally, a method is devised for a multi-factor scaling analysis. We apply the simplest, two-factor model to equity index and trading volume time series.
16 pages, 5 figures, accepted for publication in Physica A
References in corpus (7)
- Statistical Properties of Share Volume Traded in Financial Markets
- Scale Invariance in the Nonstationarity of Physiological Signals
- Do Pareto-Zipf and Gibrat laws hold true? An analysis with European Firms
- Zipf Law in Firms Bankruptcy
- Strategy for investments from Zipf law(s)
- Zipf's law in human heartbeat dynamics
- Properties of low variability periods in financial time series