Robust likelihood inference for multivariate correlated count data

Tsung Shan Tsou

doi:10.1007/s00180-015-0589-3

Robust likelihood inference for multivariate correlated count data

Tsung Shan Tsou

Graduate Institute of Statistics

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

2 Scopus citations

Abstract

A parametric robust approach for analyzing correlated count data is introduced. This method enables one to construct an asymptotically valid likelihood for the regression parameter when knowledge about the joint distribution for data is scarce or not available. We use simulations and real data analysis to demonstrate the merit of the proposed robust likelihood method.

Original language	English
Pages (from-to)	845-857
Number of pages	13
Journal	Computational Statistics
Volume	31
Issue number	3
DOIs	https://doi.org/10.1007/s00180-015-0589-3
State	Published - 1 Sep 2016

Keywords

Model misspecification
Multivariate negative binomial
Profile likelihood

Access to Document

10.1007/s00180-015-0589-3

Cite this

@article{74917beeb5f94a9cabfda47d887412dc,

title = "Robust likelihood inference for multivariate correlated count data",

abstract = "A parametric robust approach for analyzing correlated count data is introduced. This method enables one to construct an asymptotically valid likelihood for the regression parameter when knowledge about the joint distribution for data is scarce or not available. We use simulations and real data analysis to demonstrate the merit of the proposed robust likelihood method.",

keywords = "Model misspecification, Multivariate negative binomial, Profile likelihood",

author = "Tsou, {Tsung Shan}",

note = "Publisher Copyright: {\textcopyright} 2015, Springer-Verlag Berlin Heidelberg.",

year = "2016",

month = sep,

day = "1",

doi = "10.1007/s00180-015-0589-3",

language = "???core.languages.en_GB???",

volume = "31",

pages = "845--857",

journal = "Computational Statistics",

issn = "0943-4062",

number = "3",

}

TY - JOUR

T1 - Robust likelihood inference for multivariate correlated count data

AU - Tsou, Tsung Shan

PY - 2016/9/1

Y1 - 2016/9/1

N2 - A parametric robust approach for analyzing correlated count data is introduced. This method enables one to construct an asymptotically valid likelihood for the regression parameter when knowledge about the joint distribution for data is scarce or not available. We use simulations and real data analysis to demonstrate the merit of the proposed robust likelihood method.

AB - A parametric robust approach for analyzing correlated count data is introduced. This method enables one to construct an asymptotically valid likelihood for the regression parameter when knowledge about the joint distribution for data is scarce or not available. We use simulations and real data analysis to demonstrate the merit of the proposed robust likelihood method.

KW - Model misspecification

KW - Multivariate negative binomial

KW - Profile likelihood

UR - http://www.scopus.com/inward/record.url?scp=84930255210&partnerID=8YFLogxK

U2 - 10.1007/s00180-015-0589-3

DO - 10.1007/s00180-015-0589-3

M3 - 期刊論文

AN - SCOPUS:84930255210

SN - 0943-4062

VL - 31

SP - 845

EP - 857

JO - Computational Statistics

JF - Computational Statistics

IS - 3

ER -

Robust likelihood inference for multivariate correlated count data

Abstract

Keywords

Access to Document

Fingerprint

Cite this