Multivariate time series analysis with state space models (Q1116606)

From MaRDI portal
scientific article
Language Label Description Also known as
English
Multivariate time series analysis with state space models
scientific article

    Statements

    Multivariate time series analysis with state space models (English)
    0 references
    1989
    0 references
    The paper proposes a method for estimating linear, time-invariant state space models from multiple time series data. The approach is based on stochastic realization theory. The coefficient matrices of the state space model are derived from the estimated Markov parameters that are associated with the different system inputs, such as lagged endogenous variables, observable exogenous variables and unobservable noise.
    0 references
    0 references
    autoregressive processes
    0 references
    moving average processes
    0 references
    estimating linear, time-invariant state space models
    0 references
    multiple time series data
    0 references
    stochastic realization theory
    0 references
    estimated Markov parameters
    0 references
    lagged endogenous variables
    0 references
    observable exogenous variables
    0 references
    unobservable noise
    0 references
    0 references
    0 references
    0 references
    0 references