Previous |  Up |  Next

Article

Title: AR models with uniformly distributed noise (English)
Author: Horváth, Michal
Language: English
Journal: Aplikace matematiky
ISSN: 0373-6725
Volume: 34
Issue: 5
Year: 1989
Pages: 396-401
Summary lang: English
Summary lang: Russian
Summary lang: Slovak
.
Category: math
.
Summary: AR models are frequently used but usually with normally distributed white noise. In this paper AR model with uniformly distributed white noise are introduces. The maximum likelihood estimation of unknown parameters is treated, iterative method for the calculation of estimates is presented. A numerical example of this procedure and simulation results are also given. (English)
Keyword: parameter estimation
Keyword: autoregressive models
Keyword: white noise
Keyword: conditional maximum likelihood method
Keyword: maximum likelihood estimation
Keyword: iterative method
Keyword: numerical example
Keyword: AR model
MSC: 62M10
MSC: 65C99
MSC: 65U05
idZBL: Zbl 0694.65075
idMR: MR1014080
DOI: 10.21136/AM.1989.104367
.
Date available: 2008-05-20T18:37:30Z
Last updated: 2020-07-28
Stable URL: http://hdl.handle.net/10338.dmlcz/104367
.
Reference: [1] G. E. P. Box G. M. Jenkins: Time Series Analysis: Forecasting and Control.Holden-Day, San Francisco 1970. MR 0272138
Reference: [2] N. Davies T. Spedding W. Watson: Autoregressive moving average process with non-normal residueals.J. Time Series Anal. 2 (1980), 155-171.
Reference: [3] A. J. Lawrence P. A. W. Lewis: The exponential autoregressive moving - average EARMA $(p, q)$ process.J. Roy. Statist. Soc., B 42 (1980), 150-161, MR 0583349
Reference: [4] R. D. Martin V. J. Yohai: Robustness in Time Series and Estimating ARMA Models.Proc. Handbook of Statistics 5 Time Series in the Time Domain, Elsevier, Amsterdam 1985. MR 0831746
Reference: [5] R. L. Kashyap A. R. Rao: Dynamic Stochastic Models from Empirical Data.Academic Press, New York 1976.
.

Files

Files Size Format View
AplMat_34-1989-5_6.pdf 799.6Kb application/pdf View/Open
Back to standard record
Partner of
EuDML logo