On the statistical analysis of quantized Gaussian AR(1) processes

M. Rasonyi

doi:10.1002/acs.1145

On the statistical analysis of quantized Gaussian AR(1) processes

M. Rasonyi

School of Mathematics

Research output: Contribution to journal › Article › peer-review

Abstract

A discrete-time stable Gaussian autoregressive process is considered, which is observed with a fixed precision only. A law of large numbers-uniformly in the autoregression, mean and variance parameters-is proved for the log-likelihood function of the observations through establishing a mixing property. Exponential stability of the corresponding filter is also derived.

Original language	English
Pages (from-to)	490-507
Number of pages	18
Journal	International journal of adaptive control and signal processing
Volume	24
Issue number	6
DOIs	https://doi.org/10.1002/acs.1145
Publication status	Published - Jun 2010

Keywords / Materials (for Non-textual outputs)

system identification
Gaussian ARMA processes
quantized observations
law of large numbers
log-likelihood function
maximum likelihood estimators
EXPONENTIAL STABILITY
ERRORS

Access to Document

10.1002/acs.1145

http://onlinelibrary.wiley.com/doi/10.1002/acs.1145/abstract;jsessionid=EA236A20A88B34780D1640EC731F9968.d02t03

Cite this

@article{959b9dfe671d47bbbd31bd193724f292,

title = "On the statistical analysis of quantized Gaussian AR(1) processes",

abstract = "A discrete-time stable Gaussian autoregressive process is considered, which is observed with a fixed precision only. A law of large numbers-uniformly in the autoregression, mean and variance parameters-is proved for the log-likelihood function of the observations through establishing a mixing property. Exponential stability of the corresponding filter is also derived.",

keywords = "system identification, Gaussian ARMA processes, quantized observations, law of large numbers, log-likelihood function, maximum likelihood estimators, EXPONENTIAL STABILITY, ERRORS",

author = "M. Rasonyi",

year = "2010",

month = jun,

doi = "10.1002/acs.1145",

language = "English",

volume = "24",

pages = "490--507",

journal = "International journal of adaptive control and signal processing",

issn = "0890-6327",

publisher = "Wiley",

number = "6",

}

TY - JOUR

T1 - On the statistical analysis of quantized Gaussian AR(1) processes

AU - Rasonyi, M.

PY - 2010/6

Y1 - 2010/6

N2 - A discrete-time stable Gaussian autoregressive process is considered, which is observed with a fixed precision only. A law of large numbers-uniformly in the autoregression, mean and variance parameters-is proved for the log-likelihood function of the observations through establishing a mixing property. Exponential stability of the corresponding filter is also derived.

AB - A discrete-time stable Gaussian autoregressive process is considered, which is observed with a fixed precision only. A law of large numbers-uniformly in the autoregression, mean and variance parameters-is proved for the log-likelihood function of the observations through establishing a mixing property. Exponential stability of the corresponding filter is also derived.

KW - system identification

KW - Gaussian ARMA processes

KW - quantized observations

KW - law of large numbers

KW - log-likelihood function

KW - maximum likelihood estimators

KW - EXPONENTIAL STABILITY

KW - ERRORS

UR - http://www.scopus.com/inward/record.url?scp=77952975331&partnerID=8YFLogxK

U2 - 10.1002/acs.1145

DO - 10.1002/acs.1145

M3 - Article

SN - 0890-6327

VL - 24

SP - 490

EP - 507

JO - International journal of adaptive control and signal processing

JF - International journal of adaptive control and signal processing

IS - 6

ER -

On the statistical analysis of quantized Gaussian AR(1) processes

Abstract

Keywords / Materials (for Non-textual outputs)

Access to Document

Other files and links

Fingerprint

Cite this