Local influence assessment in the growth curve model with unstructured covariance

Jian Xin Pan; Kai Tai Fang; Dietrich Von Rosen

doi:10.1016/s0378-3758(96)00194-2

Local influence assessment in the growth curve model with unstructured covariance

Jian Xin Pan, Kai Tai Fang, Dietrich Von Rosen^*

^*Corresponding author for this work

Department of Mathematics

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

18 Citations (Scopus)

Abstract

In this paper, a local influence approach is employed to assess adequacy of the growth curve model with an unstructured covariance, based on likelihood displacement. The Hessian matrix of the model is investigated in detail under an abstract perturbation scheme. For illustration, covariance-weighted perturbation is discussed and used to analyze two real-life biological data sets, which show that the criteria presented in this article are useful in practice.

Original language	English
Pages (from-to)	263-278
Number of pages	16
Journal	Journal of Statistical Planning and Inference
Volume	62
Issue number	2
DOIs	https://doi.org/10.1016/s0378-3758(96)00194-2
Publication status	Published - 15 Aug 1997

Scopus Subject Areas

Statistics and Probability
Statistics, Probability and Uncertainty
Applied Mathematics

User-Defined Keywords

Curvature
Growth curve model
Hessian matrix
Likelihood displacement
Local influence
Perturbation
Statistical diagnostic

Access to Document

10.1016/s0378-3758(96)00194-2

Cite this

@article{793f2046222541599078444234cfcebe,

title = "Local influence assessment in the growth curve model with unstructured covariance",

abstract = "In this paper, a local influence approach is employed to assess adequacy of the growth curve model with an unstructured covariance, based on likelihood displacement. The Hessian matrix of the model is investigated in detail under an abstract perturbation scheme. For illustration, covariance-weighted perturbation is discussed and used to analyze two real-life biological data sets, which show that the criteria presented in this article are useful in practice.",

keywords = "Curvature, Growth curve model, Hessian matrix, Likelihood displacement, Local influence, Perturbation, Statistical diagnostic",

author = "Pan, {Jian Xin} and Fang, {Kai Tai} and {Von Rosen}, Dietrich",

note = "Funding Information: where X and Z are known design matrices of ranks m < p and r < n, respectively, and B is an unknown regression coefficient matrix. The columns of the error matrix E are independent p-variate normal with mean 0 and unknown covariance matrix I; > 0, i.e, Y ~ Np, n(XBZ, X, ln). Usually, p is the number of time points observed on each of * Corresponding author. E-mail: dietrich@math.uu.se. J Supported partially by the Hong Kong UPGC Grant and the Swedish Natural Research Council.",

year = "1997",

month = aug,

day = "15",

doi = "10.1016/s0378-3758(96)00194-2",

language = "English",

volume = "62",

pages = "263--278",

journal = "Journal of Statistical Planning and Inference",

issn = "0378-3758",

publisher = "Elsevier",

number = "2",

}

TY - JOUR

T1 - Local influence assessment in the growth curve model with unstructured covariance

AU - Pan, Jian Xin

AU - Fang, Kai Tai

AU - Von Rosen, Dietrich

N1 - Funding Information: where X and Z are known design matrices of ranks m < p and r < n, respectively, and B is an unknown regression coefficient matrix. The columns of the error matrix E are independent p-variate normal with mean 0 and unknown covariance matrix I; > 0, i.e, Y ~ Np, n(XBZ, X, ln). Usually, p is the number of time points observed on each of * Corresponding author. E-mail: dietrich@math.uu.se. J Supported partially by the Hong Kong UPGC Grant and the Swedish Natural Research Council.

PY - 1997/8/15

Y1 - 1997/8/15

N2 - In this paper, a local influence approach is employed to assess adequacy of the growth curve model with an unstructured covariance, based on likelihood displacement. The Hessian matrix of the model is investigated in detail under an abstract perturbation scheme. For illustration, covariance-weighted perturbation is discussed and used to analyze two real-life biological data sets, which show that the criteria presented in this article are useful in practice.

AB - In this paper, a local influence approach is employed to assess adequacy of the growth curve model with an unstructured covariance, based on likelihood displacement. The Hessian matrix of the model is investigated in detail under an abstract perturbation scheme. For illustration, covariance-weighted perturbation is discussed and used to analyze two real-life biological data sets, which show that the criteria presented in this article are useful in practice.

KW - Curvature

KW - Growth curve model

KW - Hessian matrix

KW - Likelihood displacement

KW - Local influence

KW - Perturbation

KW - Statistical diagnostic

UR - http://www.scopus.com/inward/record.url?scp=0031571477&partnerID=8YFLogxK

U2 - 10.1016/s0378-3758(96)00194-2

DO - 10.1016/s0378-3758(96)00194-2

M3 - Article

AN - SCOPUS:0031571477

SN - 0378-3758

VL - 62

SP - 263

EP - 278

JO - Journal of Statistical Planning and Inference

JF - Journal of Statistical Planning and Inference

IS - 2

ER -

Local influence assessment in the growth curve model with unstructured covariance

Abstract

Scopus Subject Areas

User-Defined Keywords

Access to Document

Other files and links

Fingerprint

Cite this