Graphical modeling of stochastic processes driven by correlated errors
arXiv:2005.07568 · doi:10.3150/21-BEJ1446
Abstract
We study a class of graphs that represent local independence structures in stochastic processes allowing for correlated error processes. Several graphs may encode the same local independencies and we characterize such equivalence classes of graphs. In the worst case, the number of conditions in our characterizations grows superpolynomially as a function of the size of the node set in the graph. We show that deciding Markov equivalence is coNP-complete which suggests that our characterizations cannot be improved upon substantially. We prove a global Markov property in the case of a multivariate Ornstein-Uhlenbeck process which is driven by correlated Brownian motions.
arXiv comment43 pages
References in corpus (17)
- Threshold Regression for Survival Analysis: Modeling Event Times by a Stochastic Process Reaching a Boundary
- Large-Sample Learning of Bayesian Networks is NP-Hard
- Directed Cyclic Graphical Representations of Feedback Models
- Graphical modelling of multivariate time series
- A Discovery Algorithm for Directed Cyclic Graphs
- Markov equivalence for ancestral graphs
- Complexity of Inference in Graphical Models
- Graphical models for marked point processes based on local independence
- The Ornstein-Uhlenbeck process with migration: evolution with interactions
- Causal interpretation of stochastic differential equations
- A Polynomial-Time Algorithm for Deciding Markov Equivalence of Directed Cyclic Graphical Models
- Markov equivalence of marginalized local independence graphs
- Finding a Path is Harder than Finding a Tree
- Counterfactual analyses with graphical models based on local independence
- Causal Discovery from Subsampled Time Series Data by Constraint Optimization
- Graphical modeling of stochastic processes driven by correlated errors
- Option pricing under Ornstein-Uhlenbeck stochastic volatility: a linear model