Minimum message length analysis of multiple short time series

Daniel F. Schmidt; Enes Makalic

doi:10.1016/j.spl.2015.09.021

Minimum message length analysis of multiple short time series

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

Abstract

This paper applies the Bayesian minimum message length principle to the multiple short time series problem, yielding satisfactory estimates for all model parameters as well as a test for autocorrelation. Connections with the method of conditional likelihood are also discussed.

Original language	English
Pages (from-to)	318-328
Number of pages	11
Journal	Statistics and Probability Letters
Volume	110
DOIs	https://doi.org/10.1016/j.spl.2015.09.021
Publication status	Published - Mar 2016
Externally published	Yes

Keywords

Approximate conditional likelihood
Bayesian inference
Gaussian autoregressive processes
Minimum message length
Nuisance parameters

Access to Document

10.1016/j.spl.2015.09.021

Cite this

@article{e75b7aacc4b345459e968168ffa978a2,

title = "Minimum message length analysis of multiple short time series",

abstract = "This paper applies the Bayesian minimum message length principle to the multiple short time series problem, yielding satisfactory estimates for all model parameters as well as a test for autocorrelation. Connections with the method of conditional likelihood are also discussed.",

keywords = "Approximate conditional likelihood, Bayesian inference, Gaussian autoregressive processes, Minimum message length, Nuisance parameters",

author = "Schmidt, \{Daniel F.\} and Enes Makalic",

year = "2016",

month = mar,

doi = "10.1016/j.spl.2015.09.021",

language = "English",

volume = "110",

pages = "318--328",

journal = "Statistics and Probability Letters",

issn = "0167-7152",

publisher = "Elsevier",

}

TY - JOUR

T1 - Minimum message length analysis of multiple short time series

AU - Schmidt, Daniel F.

AU - Makalic, Enes

PY - 2016/3

Y1 - 2016/3

N2 - This paper applies the Bayesian minimum message length principle to the multiple short time series problem, yielding satisfactory estimates for all model parameters as well as a test for autocorrelation. Connections with the method of conditional likelihood are also discussed.

AB - This paper applies the Bayesian minimum message length principle to the multiple short time series problem, yielding satisfactory estimates for all model parameters as well as a test for autocorrelation. Connections with the method of conditional likelihood are also discussed.

KW - Approximate conditional likelihood

KW - Bayesian inference

KW - Gaussian autoregressive processes

KW - Minimum message length

KW - Nuisance parameters

UR - https://www.scopus.com/pages/publications/84960796710

U2 - 10.1016/j.spl.2015.09.021

DO - 10.1016/j.spl.2015.09.021

M3 - Article

AN - SCOPUS:84960796710

SN - 0167-7152

VL - 110

SP - 318

EP - 328

JO - Statistics and Probability Letters

JF - Statistics and Probability Letters

ER -

Minimum message length analysis of multiple short time series

Abstract

Keywords

Access to Document

Other files and links

Cite this