ESTIMATION FOR REGRESSIVE AND AUTOREGRESSIVE MODELS WITH NON-NEGATIVE RESIDUAL ERRORS

DOI10.1111/J.1467-9892.1993.TB00136.XMaRDI QIDQ4696574zbMATH OpenOpenAlexFDO

Authors Hongzhi An, Fuchun Huang

Publication date 29 June 1993

Published in Journal of Time Series Analysis (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1111/j.1467-9892.1993.tb00136.x

zbMATH Keywords

\(AR(p)\) modelautoregressive modelexponential distributionmaximum likelihood estimatorsrates of almost sure convergenceregressive modelresidual errorsimulation studies

Mathematics Subject Classification ID

Estimation in multivariate analysis (62H12) Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10)

Review text

The authors discuss parameter estimation when the residual error in a regressive model or in an autoregressive model of order \(p\) \((AR(p))\) is an independently and identically distributed sequence of non-negative random variables. They propose new estimators for the regression coefficients, which are different from the least squares estimators. The estimators proposed can be obtained by solving a linear programming problem. They correspond to the maximum likelihood estimators of the regression coefficients when the residual error has an exponential distribution. The authors show the rates of almost sure convergence of the estimators to the true values when the sample size tends to infinity in both the regressive model and in the \(AR(p)\) model, under some conditions. Also, they give results of some simulation studies.

Recommendations

• scientific article; zbMATH DE number 562293
• NON‐NEGATIVE AUTOREGRESSIVE MODELS
• ESTIMATION FOR NONNEGATIVE AUTOREGRESSIVE PROCESSES WITH AN UNKNOWN LOCATION PARAMETER
• Nonlinear Autoregression with Positive Innovations
• Bootstrap, modified maximum likelihood and moment estimators comparison for parameters of autoregressive model with non-negative residuals

Cites work

• Autocorrelation, autoregression and autoregressive approximation
• scientific article; zbMATH DE number 3502497 (Why is no real title available?)
• Infrence for non-negative autoregressive schemes

Cited in

(3)

• An estimator for parameters of a nonlinear nonnegative multidimensional AR(1) process
• Bootstrap, modified maximum likelihood and moment estimators comparison for parameters of autoregressive model with non-negative residuals
• scientific article; zbMATH DE number 6193729 (Why is no real title available?)

This page was built for publication: ESTIMATION FOR REGRESSIVE AND AUTOREGRESSIVE MODELS WITH NON-NEGATIVE RESIDUAL ERRORS

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4696574)