Linear mixed effects models with flexible generalized skew-elliptical random effects

Yanyuan Ma, Marc G. Genton, Marie Davidian

Research output: Chapter in Book/Report/Conference proceedingChapter

24 Citations (Scopus)

Abstract

The linear mixed effects model is a popular framework for analysis of continuous longitudinal responses from a sample of individuals in biomedical, agricultural, environmental, and social science applications. Inter-individual heterogeneity in features of the longitudinal profiles, such as (error-free) baseline response or rate of change, is represented explicitly by individualspecific random effects, so that inference on questions involving population or individual characteristics is possible. A standard assumption is that the random effects and within-individual errors are normally distributed, and software such as SAS proc mixed (Littell, Milliken, Stroup, and Wolfinger, 1996) or Splus lme() (Pinheiro and Bates, 2000) incorporates this assumption. Although normality of within-individual deviations may be a reasonable model for many continuous measurements, perhaps on a transformed scale, normality of the random effects implies a belief about inter-individual heterogeneity that may be unrealistic. For example, a common feature in biological contexts is skewness or heavy-tailedness of features underlying individual profiles.

Original languageEnglish (US)
Title of host publicationSkew-Elliptical Distributions and Their Applications
Subtitle of host publicationA Journey Beyond Normality
PublisherCRC Press
Pages339-358
Number of pages20
ISBN (Electronic)9780203492000
ISBN (Print)9781584884316
StatePublished - Jan 1 2004

Fingerprint

Linear Mixed Effects Model
Random Effects
Skew
Normality
Rate of change
Social Sciences
Skewness
Baseline
Deviation
Imply
Software
Profile
Model

All Science Journal Classification (ASJC) codes

  • Mathematics(all)

Cite this

Ma, Y., Genton, M. G., & Davidian, M. (2004). Linear mixed effects models with flexible generalized skew-elliptical random effects. In Skew-Elliptical Distributions and Their Applications: A Journey Beyond Normality (pp. 339-358). CRC Press.
Ma, Yanyuan ; Genton, Marc G. ; Davidian, Marie. / Linear mixed effects models with flexible generalized skew-elliptical random effects. Skew-Elliptical Distributions and Their Applications: A Journey Beyond Normality. CRC Press, 2004. pp. 339-358
@inbook{e7fec9a9705442babeaef9e7e33806c3,
title = "Linear mixed effects models with flexible generalized skew-elliptical random effects",
abstract = "The linear mixed effects model is a popular framework for analysis of continuous longitudinal responses from a sample of individuals in biomedical, agricultural, environmental, and social science applications. Inter-individual heterogeneity in features of the longitudinal profiles, such as (error-free) baseline response or rate of change, is represented explicitly by individualspecific random effects, so that inference on questions involving population or individual characteristics is possible. A standard assumption is that the random effects and within-individual errors are normally distributed, and software such as SAS proc mixed (Littell, Milliken, Stroup, and Wolfinger, 1996) or Splus lme() (Pinheiro and Bates, 2000) incorporates this assumption. Although normality of within-individual deviations may be a reasonable model for many continuous measurements, perhaps on a transformed scale, normality of the random effects implies a belief about inter-individual heterogeneity that may be unrealistic. For example, a common feature in biological contexts is skewness or heavy-tailedness of features underlying individual profiles.",
author = "Yanyuan Ma and Genton, {Marc G.} and Marie Davidian",
year = "2004",
month = "1",
day = "1",
language = "English (US)",
isbn = "9781584884316",
pages = "339--358",
booktitle = "Skew-Elliptical Distributions and Their Applications",
publisher = "CRC Press",

}

Ma, Y, Genton, MG & Davidian, M 2004, Linear mixed effects models with flexible generalized skew-elliptical random effects. in Skew-Elliptical Distributions and Their Applications: A Journey Beyond Normality. CRC Press, pp. 339-358.

Linear mixed effects models with flexible generalized skew-elliptical random effects. / Ma, Yanyuan; Genton, Marc G.; Davidian, Marie.

Skew-Elliptical Distributions and Their Applications: A Journey Beyond Normality. CRC Press, 2004. p. 339-358.

Research output: Chapter in Book/Report/Conference proceedingChapter

TY - CHAP

T1 - Linear mixed effects models with flexible generalized skew-elliptical random effects

AU - Ma, Yanyuan

AU - Genton, Marc G.

AU - Davidian, Marie

PY - 2004/1/1

Y1 - 2004/1/1

N2 - The linear mixed effects model is a popular framework for analysis of continuous longitudinal responses from a sample of individuals in biomedical, agricultural, environmental, and social science applications. Inter-individual heterogeneity in features of the longitudinal profiles, such as (error-free) baseline response or rate of change, is represented explicitly by individualspecific random effects, so that inference on questions involving population or individual characteristics is possible. A standard assumption is that the random effects and within-individual errors are normally distributed, and software such as SAS proc mixed (Littell, Milliken, Stroup, and Wolfinger, 1996) or Splus lme() (Pinheiro and Bates, 2000) incorporates this assumption. Although normality of within-individual deviations may be a reasonable model for many continuous measurements, perhaps on a transformed scale, normality of the random effects implies a belief about inter-individual heterogeneity that may be unrealistic. For example, a common feature in biological contexts is skewness or heavy-tailedness of features underlying individual profiles.

AB - The linear mixed effects model is a popular framework for analysis of continuous longitudinal responses from a sample of individuals in biomedical, agricultural, environmental, and social science applications. Inter-individual heterogeneity in features of the longitudinal profiles, such as (error-free) baseline response or rate of change, is represented explicitly by individualspecific random effects, so that inference on questions involving population or individual characteristics is possible. A standard assumption is that the random effects and within-individual errors are normally distributed, and software such as SAS proc mixed (Littell, Milliken, Stroup, and Wolfinger, 1996) or Splus lme() (Pinheiro and Bates, 2000) incorporates this assumption. Although normality of within-individual deviations may be a reasonable model for many continuous measurements, perhaps on a transformed scale, normality of the random effects implies a belief about inter-individual heterogeneity that may be unrealistic. For example, a common feature in biological contexts is skewness or heavy-tailedness of features underlying individual profiles.

UR - http://www.scopus.com/inward/record.url?scp=78650411654&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78650411654&partnerID=8YFLogxK

M3 - Chapter

AN - SCOPUS:78650411654

SN - 9781584884316

SP - 339

EP - 358

BT - Skew-Elliptical Distributions and Their Applications

PB - CRC Press

ER -

Ma Y, Genton MG, Davidian M. Linear mixed effects models with flexible generalized skew-elliptical random effects. In Skew-Elliptical Distributions and Their Applications: A Journey Beyond Normality. CRC Press. 2004. p. 339-358