Functional random effect time-varying coefficient model for longitudinal data

Jeng Min Chiou, Yanyuan Ma, Chih Ling Tsai

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

We propose a functional random effect time-varying coefficient model to establish the dynamic relationship between the response and predictor variables in longitudinal data. This model allows us not only to interpret time-varying covariate effects, but also to depict random effects via time-varying profiles that are characterized by functional principal components. We develop the functional profiling-backfitting method to estimate model components, which includes the profiling and backfitting procedures via a set of least squares type estimating equations. Asymptotic properties of the resulting estimator are obtained. Furthermore, we investigate the finite sample performance of the proposed method through simulation studies and present an application to primary biliary cirrhosis data.

Original languageEnglish (US)
Pages (from-to)75-89
Number of pages15
JournalStat
Volume1
Issue number1
DOIs
StatePublished - Jan 1 2012

Fingerprint

Backfitting
Time-varying Coefficients
Varying Coefficient Model
Longitudinal Data
Profiling
Random Effects
Time-varying Covariates
Estimating Equation
Component Model
Principal Components
Asymptotic Properties
Least Squares
Predictors
Time-varying
Simulation Study
Estimator
Estimate
Time-varying coefficient model
Random effects
Longitudinal data

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

Chiou, Jeng Min ; Ma, Yanyuan ; Tsai, Chih Ling. / Functional random effect time-varying coefficient model for longitudinal data. In: Stat. 2012 ; Vol. 1, No. 1. pp. 75-89.
@article{f9d312251a354dc8a3379d3255c238d4,
title = "Functional random effect time-varying coefficient model for longitudinal data",
abstract = "We propose a functional random effect time-varying coefficient model to establish the dynamic relationship between the response and predictor variables in longitudinal data. This model allows us not only to interpret time-varying covariate effects, but also to depict random effects via time-varying profiles that are characterized by functional principal components. We develop the functional profiling-backfitting method to estimate model components, which includes the profiling and backfitting procedures via a set of least squares type estimating equations. Asymptotic properties of the resulting estimator are obtained. Furthermore, we investigate the finite sample performance of the proposed method through simulation studies and present an application to primary biliary cirrhosis data.",
author = "Chiou, {Jeng Min} and Yanyuan Ma and Tsai, {Chih Ling}",
year = "2012",
month = "1",
day = "1",
doi = "10.1002/sta4.10",
language = "English (US)",
volume = "1",
pages = "75--89",
journal = "Stat",
issn = "2049-1573",
publisher = "Wiley-Blackwell",
number = "1",

}

Functional random effect time-varying coefficient model for longitudinal data. / Chiou, Jeng Min; Ma, Yanyuan; Tsai, Chih Ling.

In: Stat, Vol. 1, No. 1, 01.01.2012, p. 75-89.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Functional random effect time-varying coefficient model for longitudinal data

AU - Chiou, Jeng Min

AU - Ma, Yanyuan

AU - Tsai, Chih Ling

PY - 2012/1/1

Y1 - 2012/1/1

N2 - We propose a functional random effect time-varying coefficient model to establish the dynamic relationship between the response and predictor variables in longitudinal data. This model allows us not only to interpret time-varying covariate effects, but also to depict random effects via time-varying profiles that are characterized by functional principal components. We develop the functional profiling-backfitting method to estimate model components, which includes the profiling and backfitting procedures via a set of least squares type estimating equations. Asymptotic properties of the resulting estimator are obtained. Furthermore, we investigate the finite sample performance of the proposed method through simulation studies and present an application to primary biliary cirrhosis data.

AB - We propose a functional random effect time-varying coefficient model to establish the dynamic relationship between the response and predictor variables in longitudinal data. This model allows us not only to interpret time-varying covariate effects, but also to depict random effects via time-varying profiles that are characterized by functional principal components. We develop the functional profiling-backfitting method to estimate model components, which includes the profiling and backfitting procedures via a set of least squares type estimating equations. Asymptotic properties of the resulting estimator are obtained. Furthermore, we investigate the finite sample performance of the proposed method through simulation studies and present an application to primary biliary cirrhosis data.

UR - http://www.scopus.com/inward/record.url?scp=84942636660&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84942636660&partnerID=8YFLogxK

U2 - 10.1002/sta4.10

DO - 10.1002/sta4.10

M3 - Article

VL - 1

SP - 75

EP - 89

JO - Stat

JF - Stat

SN - 2049-1573

IS - 1

ER -