On nonlinear random effects models for repeated measurements

Kathryn Hirst, Gary O. Zerbe, David Boyle, Randall B. Wilkening

Research output: Contribution to journalArticle

34 Citations (Scopus)

Abstract

Linear random effects models for longitudinal data discussed by Laird and Ware (1982), Jennrich and Schluchter (1986), Lange and Laird (1989), and others are extended in a straight forward manner to nonlinear random effects models. This results in a simple computational approach which accommodates patterned covariance matrices and data insufficient for fitting each subject separately. The technique is demonstrated with an interesting medical data set, and a short, simple SAS PROC IML program based on the EM algorithm is presented.

Original languageEnglish (US)
Pages (from-to)463-478
Number of pages16
JournalCommunications in Statistics: Simulation and Computation
Volume20
Issue number2-3
DOIs
StatePublished - Jan 1 1991
Externally publishedYes

Fingerprint

Repeated Measurements
Random Effects Model
Nonlinear Effects
Nonlinear Model
Longitudinal Data
EM Algorithm
Covariance matrix
Straight
Linear Model

Keywords

  • algorithm
  • EM
  • longitudinal data
  • nonlinear mixed effects model
  • stochastic parameters

ASJC Scopus subject areas

  • Modeling and Simulation
  • Statistics and Probability

Cite this

On nonlinear random effects models for repeated measurements. / Hirst, Kathryn; Zerbe, Gary O.; Boyle, David; Wilkening, Randall B.

In: Communications in Statistics: Simulation and Computation, Vol. 20, No. 2-3, 01.01.1991, p. 463-478.

Research output: Contribution to journalArticle

Hirst, Kathryn ; Zerbe, Gary O. ; Boyle, David ; Wilkening, Randall B. / On nonlinear random effects models for repeated measurements. In: Communications in Statistics: Simulation and Computation. 1991 ; Vol. 20, No. 2-3. pp. 463-478.
@article{b489bc7f80d14af1b3ff8a707671dfa4,
title = "On nonlinear random effects models for repeated measurements",
abstract = "Linear random effects models for longitudinal data discussed by Laird and Ware (1982), Jennrich and Schluchter (1986), Lange and Laird (1989), and others are extended in a straight forward manner to nonlinear random effects models. This results in a simple computational approach which accommodates patterned covariance matrices and data insufficient for fitting each subject separately. The technique is demonstrated with an interesting medical data set, and a short, simple SAS PROC IML program based on the EM algorithm is presented.",
keywords = "algorithm, EM, longitudinal data, nonlinear mixed effects model, stochastic parameters",
author = "Kathryn Hirst and Zerbe, {Gary O.} and David Boyle and Wilkening, {Randall B.}",
year = "1991",
month = "1",
day = "1",
doi = "10.1080/03610919108812966",
language = "English (US)",
volume = "20",
pages = "463--478",
journal = "Communications in Statistics Part B: Simulation and Computation",
issn = "0361-0918",
publisher = "Taylor and Francis Ltd.",
number = "2-3",

}

TY - JOUR

T1 - On nonlinear random effects models for repeated measurements

AU - Hirst, Kathryn

AU - Zerbe, Gary O.

AU - Boyle, David

AU - Wilkening, Randall B.

PY - 1991/1/1

Y1 - 1991/1/1

N2 - Linear random effects models for longitudinal data discussed by Laird and Ware (1982), Jennrich and Schluchter (1986), Lange and Laird (1989), and others are extended in a straight forward manner to nonlinear random effects models. This results in a simple computational approach which accommodates patterned covariance matrices and data insufficient for fitting each subject separately. The technique is demonstrated with an interesting medical data set, and a short, simple SAS PROC IML program based on the EM algorithm is presented.

AB - Linear random effects models for longitudinal data discussed by Laird and Ware (1982), Jennrich and Schluchter (1986), Lange and Laird (1989), and others are extended in a straight forward manner to nonlinear random effects models. This results in a simple computational approach which accommodates patterned covariance matrices and data insufficient for fitting each subject separately. The technique is demonstrated with an interesting medical data set, and a short, simple SAS PROC IML program based on the EM algorithm is presented.

KW - algorithm

KW - EM

KW - longitudinal data

KW - nonlinear mixed effects model

KW - stochastic parameters

UR - http://www.scopus.com/inward/record.url?scp=0000177620&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0000177620&partnerID=8YFLogxK

U2 - 10.1080/03610919108812966

DO - 10.1080/03610919108812966

M3 - Article

VL - 20

SP - 463

EP - 478

JO - Communications in Statistics Part B: Simulation and Computation

JF - Communications in Statistics Part B: Simulation and Computation

SN - 0361-0918

IS - 2-3

ER -