On multi-step MLE-process for Markov sequences

DOI10.1007/S00184-015-0574-4MaRDI QIDQ310050zbMATH OpenOpenAlexFDO

Authors A. Motrunich, Yu. A. Kutoyants

Publication date 7 September 2016

Published in Metrika (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1601.08174

zbMATH Keywords

asymptotic properties of estimatorsnonlinear autoregressive processtwo or three steps estimation procedures

Mathematics Subject Classification ID

Asymptotic properties of parametric estimators (62F12) Markov processes: estimation; hidden Markov models (62M05) Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10)

Abstract: We consider the problem of the construction of the estimator-process of the unknown finite-dimensional parameter in the case of the observations of nonlinear autoregressive process. The estimation is done in two or three steps. First we estimate the unknown parameter by a learning relatively short part of observations and then we use the one-step MLE idea to construct an-estimator process which is asymptotically equivalent to the MLE. To have the learning interval shorter we introduce the two-step procedure which leads to the asymptotically efficient estimator-process too. The presented results are illustrated with the help of two numerical examples.

Review text

From the text: ``The problem of the construction of the estimator-process of the unknown finite-dimensional parameter in the case of the observations of nonlinear autoregressive process is considered. It is supposed that the noise distribution is completely known and the process is stationary with a unique invariant distribution. ``The estimation is done in two or three steps. In the two-step procedure the series \(X_0,\dots,X_n\) is split into two parts. The first learning interval \([0,N]\) is used to get a preliminary estimator, e.g. a MLE or a Bayes estimator or a moment estimator. Using this estimator, an iteratively defined MLE process based on the normalized score function is created. In case \(N=n^{\delta}\), \(1/2<\delta < 1\), it is proved that the MLE process is asymptotically normal and efficient in \((0,1]\). In case \(N=n^{\delta}\), \(1/4 \delta \leq 1/2\), the authors suggest a three-step procedure. As the preliminary estimator may not have the right rate of convergence, the second preliminary estimator process is created and then in the third step an asymptotically efficient estimator process is obtained. The procedures are illustrated by two examples. In the first example a two-step procedure is applied with a preliminary estimator obtained by the maximum likelihood method. In the second example a three-step procedure is used with a preliminary moment estimator based on \(N=n^{3/8}\) observations.

Recommendations

• On the multi-step MLE-process for ergodic diffusion
• Maximum likelihood estimators in nonlinear autoregressive processes
• Method of moments estimators and multi-step MLE for Poisson processes
• Consistent Estimation of Linear and Non-linear Autoregressive Models with Markov Regime
• Adaptive estimators for parameters of the autoregression function of a Markov chain

Cites work

• Approximation of the solution of the backward stochastic differential equation. Small noise, large sample and high frequency cases
• Asymptotic Inference in Markov Processes
• Asymptotic theory of statistical inference for time series
• Differentiability of invariant measures of diffusions with respect to a parameter
• scientific article; zbMATH DE number 3174032 (Why is no real title available?)
• scientific article; zbMATH DE number 3733065 (Why is no real title available?)
• scientific article; zbMATH DE number 1777535 (Why is no real title available?)
• Hybrid multi-step estimators for stochastic differential equations based on sampled data
• Nonlinear time series. Nonparametric and parametric methods
• On estimation and adaptive estimation for locally asymptotically normal families
• On parameter estimation from indirect observations
• The weak convergence of the likelihood ratio random fields for Markov observations

Cited in

(18)

• Method of moments estimators and multi-step MLE for Poisson processes
• MARM processes. II: The empirically-based subclass
• On parameter estimation of hidden ergodic Ornstein-Uhlenbeck process
• On parameter estimation of the hidden Gaussian process in perturbed SDE
• On approximation of BSDE and multi-step MLE-processes
• On the multi-step MLE-process for ergodic diffusion
• Asymptotic accuracy of the Aitken-Markov estimator
• One-step estimation for the fractional Gaussian noise at high-frequency
• One-step closed-form estimator for generalized linear model with categorical explanatory variables
• Fast and asymptotically efficient estimation in the Hawkes processes
• Fast and asymptotically-efficient estimation in an autoregressive process with fractional type noise
• Fast and asymptotically efficient estimation for t and log( t ) distributions
• Subsampled one-step estimation for fast statistical inference
• Parameter estimation for fractional autoregressive process with seasonal structure
• One-step statistical estimation method for generalized linear models
• Hidden ergodic Ornstein-Uhlenbeck process and adaptive filter
• Statistical inference for two-population stochastic epidemic models
• On M-processes and M-estimation

This page was built for publication: On multi-step MLE-process for Markov sequences

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q310050)