Uncovering the evolution of non-stationary stochastic variables: the example of asset volume-price fluctuations
We present a framework for describing the evolution of stochastic observables having a non-stationary distribution of values. The framework is applied to empirical volume-prices from assets traded at the New York stock exchange. Using Kullback-Leibler divergence we evaluate the best model out from four biparametric models standardly used in the context of financial data analysis. In our present data sets we conclude that the inverse $\Gamma$-distribution is a good model, particularly for the distribution tail of the largest volume-price fluctuations. Extracting the time-series of the corresponding parameter values we show that they evolve in time as stochastic variables themselves. For the particular case of the parameter controlling the volume-price distribution tail we are able to extract an Ornstein-Uhlenbeck equation which describes the fluctuations of the largest volume-prices observed in the data. Finally, we discuss how to bridge from the stochastic evolution of the distribution parameters to the stochastic evolution of the (non-stationary) observable and put our conclusions into perspective for other applications in geophysics and biology.
Code (0)
등록된 구현이 없습니다.
Tasks
GeophysicsTime SeriesTime Series AnalysisSimilar Papers 제목 키워드 기반
Kernel-based Joint Independence Tests for Multivariate Stationary and Non-stationary Time Series
Multivariate time series data that capture the temporal evolution of interconnected systems are ubiquitous in diverse areas. Understanding the complex relationships and potential dependencies among co-observed variables …
Time SeriesStochastic modelling of non-stationary financial assets
We model non-stationary volume-price distributions with a log-normal distribution and collect the time series of its two parameters. The time series of the two parameters are shown to be stationary and Markov-like and co…
Time SeriesTime Series AnalysisStationary frequencies and mixing times for neutral drift processes with spatial structure
We study a general setting of neutral evolution in which the population is of finite, constant size and can have spatial structure. Mutation leads to different genetic types ("traits"), which can be discrete or continuou…
Jacobian Granger Causal Neural Networks for Analysis of Stationary and Nonstationary Data
Granger causality is a commonly used method for uncovering information flow and dependencies in a time series. Here we introduce JGC (Jacobian Granger Causality), a neural network-based approach to Granger causality usin…
Time SeriesTime Series AnalysisContinuous-time stochastic gradient descent for optimizing over the stationary distribution of stochastic differential equations
We develop a new continuous-time stochastic gradient descent method for optimizing over the stationary distribution of stochastic differential equation (SDE) models. The algorithm continuously updates the SDE model's par…