• Corpus ID: 252531469

An implimentation of the Differential Filter for Computing Gradient and Hessian of the Log-likelihood of Nonstationary Time Series Models

@inproceedings{Kitagawa2022AnIO,
  title={An implimentation of the Differential Filter for Computing Gradient and Hessian of the Log-likelihood of Nonstationary Time Series Models},
  author={Genshiro Kitagawa},
  year={2022}
}
The state-space model and the Kalman filter provide us with unified and computationaly efficient procedure for computing the log-likelihood of the diverse type of time series models. This paper presents an algorithm for computing the gradient and the Hessian matrix of the log-likelihood by extending the Kalman filter without resorting to the numerical difference. Different from the previous paper [11], it is assumed that the observation noise variance R = 1. It is known that for univariate time series… 

Figures and Tables from this paper

References

SHOWING 1-10 OF 18 REFERENCES

Analytic Derivatives for Estimation of Linear Dynamic Models

Monte Carlo Filter and Smoother for Non-Gaussian Nonlinear State Space Models

A new algorithm based on a Monte Carlo method that can be applied to a broad class of nonlinear non-Gaussian higher dimensional state space models on the provision that the dimensions of the system noise and the observation noise are relatively low.

Likelihood Gradient Evaluation Using Square-Root Covariance Filters

A new square-root algorithm for the log-likelihood gradient (score) evaluation that avoids the use of the conventional Kalman filter with its inherent numerical instabilities and improves the robustness of computations against roundoff errors.

Computing the likelihood and its dierivatives for a gaussian ARMA model

A fast algorithm is obtained for computing the likelihood of a Gaussian ARMA (p,q) model and its derivatives by combining the algorithms of Pearlman (1980) and Ansley (1979). Only p + 3 q + 2

Non-Gaussian seasonal adjustment

A Smoothness Priors–State Space Modeling of Time Series with Trend and Seasonality

Abstract A smoothness priors modeling of time series with trends and seasonalities is shown. An observed time series is decomposed into local polynomial trend, seasonal, globally stationary

Information Criteria and Statistical Modeling

A generalized information criterion (GIC) and a bootstrap information criterion are presented, which provide unified tools for modeling and model evaluation for a diverse range of models, including various types of nonlinear models and model estimation procedures such as robust estimation, the maximum penalized likelihood method and a Bayesian approach.

The two-filter formula for smoothing and an implementation of the Gaussian-sum smoother

A Gaussian-sum smoother is developed based on the two filter formula for smoothing. This facilitates the application of non-Gaussian state space modeling to diverse problems in time series analysis.

SEASONAL ADJUSTMENT BY A BAYESIAN MODELING

The basic ideas underlying the construction of a newly introduced seasonal adjustment procedure by a Bayesian modeling are discussed in detail. Particular emphasis is placed on the use of the concept