Robust estimation for Binomial conditionally nonlinear autoregressive time series based on multivariate conditional frequencies

Kharin, Yu. S.; Voloshko, Valeriy A.

doi:10.1016/j.jmva.2021.104777

Cited by 6 publications

(2 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some results on robust inference based on Markov models for observed MDV time series are in [82] where the authors develop robust estimators for Binomial conditionally nonlinear autoregressive time series of order s, under innovation outliers with arbitrary discrete probability distribution having some fixed known expectation. In [73], the robustness of sequential testing of parametric hypotheses for M-valued Markov chains is analyzed under Tukey-Huber distortions.…”

Section: Robust Estimationmentioning

confidence: 99%

Statistical analysis of multivariate discrete-valued time series

Fokianos

Fried

Kharin

et al. 2022

Journal of Multivariate Analysis

Self Cite

View full text Add to dashboard Cite

Section: Robust Estimationmentioning

confidence: 99%

Statistical analysis of multivariate discrete-valued time series

Fokianos

Fried

Kharin

et al. 2022

Journal of Multivariate Analysis

Self Cite

View full text Add to dashboard Cite

“…the matrix corresponding to the future input-output data and the past input-output data, respectively [13][14]. And ,, uy L L f can be estimated by a least squares problem, i.e.…”

Section: Calculating the Oblique Projectionmentioning

confidence: 99%

A multivariate nonlinear dynamic programming of female figures in Qing dynasty literature

Zeng,

Zhu

2023

Applied Mathematics and Nonlinear Sciences

View full text Add to dashboard Cite

To improve the recognition of female images in Qing Dynasty literature, this paper designs a multivariate nonlinear-based image dynamic programming model. Data-driven typical correlation analysis is used to extract the key controllable variables with the strongest correlation with female image features and use them as input variables for modeling so as to make the maximum correlation between different image features and improve the modeling efficiency. The nonlinear spatial state model is established by using the subspace identification method, and the female image planning model is substituted into the multivariate nonlinear analysis, and the parameters of the nonlinear fitting function about the image planning can be obtained. The simulation analysis of the image dynamic planning model based on multivariate nonlinearity is carried out, and the results show that the average annual failure time of the model designed in this paper is 12.6 hours, and the classification accuracy in female image classification is 96.3%, and the classification time is stable at 1.162 s. The results show that the multivariate nonlinear features of the model can carry out dynamic planning of female images in Qing dynasty literature and improve the classification of image feature recognition.

show abstract

On the approximation of high-order binary Markov chains by parsimonious models

Kharin,

Voloshko

2024

Discrete Mathematics and Applications

View full text Add to dashboard Cite

We consider two parsimonious models of binary high-order Markov chains and discover their ability to approximate arbitrary high-order Markov chains. Two types of global measures for approximation accuracy are introduced, theoretical and experimental results are obtained for these measures and for the considered parsimonious models. New consistent statistical parameter estimator is constructed for parsimonious model based on two-layer artificial neural network.

show abstract

Robust estimation for Binomial conditionally nonlinear autoregressive time series based on multivariate conditional frequencies

Cited by 6 publications

References 25 publications

Statistical analysis of multivariate discrete-valued time series

Statistical analysis of multivariate discrete-valued time series

A multivariate nonlinear dynamic programming of female figures in Qing dynasty literature

On the approximation of high-order binary Markov chains by parsimonious models

Contact Info

Product

Resources

About