Maximum likelihood estimation for short time series with replicated observations : a simulation study

Ponnuthurai Ainkaran; Robert Mellor; Ponnuthurai Ainkaran

Maximum likelihood estimation for short time series with replicated observations : a simulation study

Ponnuthurai Ainkaran, Robert Mellor, Ponnuthurai Ainkaran

Research output: Contribution to journal › Article

Abstract

Analysis of a large number of independent replications from short, first order autoregressive type time series is considered. Maximum likelihood estimation (mle) procedure is discussed in both approximate and exact forms. A simulation study is carried out. It is shown that both the approximate and exact mle methods provide unbiased and very efficient (in the minimum mean square sense) estimates for the parameters.

Original language	English
Number of pages	16
Journal	InterStat : Statistics on the Internet
Publication status	Published - 2003

Keywords

time-series analysis
autocorrelation (statistics)
estimation theory
asymptotic theory
mathematical statistics
simulation methods

Cite this

@article{8f0281a14eb0423483c01f8fd08a74b2,

title = "Maximum likelihood estimation for short time series with replicated observations : a simulation study",

abstract = "Analysis of a large number of independent replications from short, first order autoregressive type time series is considered. Maximum likelihood estimation (mle) procedure is discussed in both approximate and exact forms. A simulation study is carried out. It is shown that both the approximate and exact mle methods provide unbiased and very efficient (in the minimum mean square sense) estimates for the parameters.",

keywords = "time-series analysis, autocorrelation (statistics), estimation theory, asymptotic theory, mathematical statistics, simulation methods",

author = "Ponnuthurai Ainkaran and Robert Mellor and Ponnuthurai Ainkaran",

year = "2003",

language = "English",

journal = "InterStat : Statistics on the Internet",

issn = "1941-689X",

publisher = "Virginia Tech",

}

TY - JOUR

T1 - Maximum likelihood estimation for short time series with replicated observations : a simulation study

AU - Ainkaran, Ponnuthurai

AU - Mellor, Robert

AU - Ainkaran, Ponnuthurai

PY - 2003

Y1 - 2003

N2 - Analysis of a large number of independent replications from short, first order autoregressive type time series is considered. Maximum likelihood estimation (mle) procedure is discussed in both approximate and exact forms. A simulation study is carried out. It is shown that both the approximate and exact mle methods provide unbiased and very efficient (in the minimum mean square sense) estimates for the parameters.

AB - Analysis of a large number of independent replications from short, first order autoregressive type time series is considered. Maximum likelihood estimation (mle) procedure is discussed in both approximate and exact forms. A simulation study is carried out. It is shown that both the approximate and exact mle methods provide unbiased and very efficient (in the minimum mean square sense) estimates for the parameters.

KW - time-series analysis

KW - autocorrelation (statistics)

KW - estimation theory

KW - asymptotic theory

KW - mathematical statistics

KW - simulation methods

UR - http://handle.uws.edu.au:8081/1959.7/45649

M3 - Article

SN - 1941-689X

JO - InterStat : Statistics on the Internet

JF - InterStat : Statistics on the Internet

ER -

Maximum likelihood estimation for short time series with replicated observations : a simulation study

Abstract

Keywords

Other files and links

Fingerprint

Cite this