A residuals-based transition model for longitudinal analysis with estimation in the presence of missing data

Tulay Sengul, David S. Stoffer, Nancy L. Day

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

We propose a transition model for analysing data from complex longitudinal studies. Because missing values are practically unavoidable in large longitudinal studies, we also present a two-stage imputation method for handling general patterns of missing values on both the outcome and the covariates by combining multiple imputation with stochastic regression imputation. Our model is a time-varying autoregression on the past innovations (residuals), and it can be used in cases where general dynamics must be taken into account, and where the model selection is important. The entire estimation process was carried out using available procedures in statistical packages such as SAS and S-PLUS. To illustrate the viability of the proposed model and the two-stage imputation method, we analyse data collected in an epidemiological study that focused on various factors relating to childhood growth. Finally, we present a simulation study to investigate the behaviour of our two-stage imputation procedure.

Original languageEnglish
Pages (from-to)3330-3341
Number of pages12
JournalStatistics in Medicine
Volume26
Issue number17
DOIs
StatePublished - Jul 30 2007
Externally publishedYes

Fingerprint

Longitudinal Analysis
Transition Model
Imputation
Missing Data
Longitudinal Study
Missing Values
Longitudinal Studies
Statistical package
Multiple Imputation
Autoregression
Viability
Model Selection
Covariates
Epidemiologic Studies
Time-varying
Regression
Simulation Study
Entire
Growth
Model

Keywords

  • Incomplete data
  • Innovations sequence
  • Longitudinal analysis
  • Missing data
  • Multiple imputation
  • Stochastic regression imputation
  • Time-varying autoregression

ASJC Scopus subject areas

  • Epidemiology

Cite this

A residuals-based transition model for longitudinal analysis with estimation in the presence of missing data. / Sengul, Tulay; Stoffer, David S.; Day, Nancy L.

In: Statistics in Medicine, Vol. 26, No. 17, 30.07.2007, p. 3330-3341.

Research output: Contribution to journalArticle

@article{05e5abec508348b98d7710a2aded132e,
title = "A residuals-based transition model for longitudinal analysis with estimation in the presence of missing data",
abstract = "We propose a transition model for analysing data from complex longitudinal studies. Because missing values are practically unavoidable in large longitudinal studies, we also present a two-stage imputation method for handling general patterns of missing values on both the outcome and the covariates by combining multiple imputation with stochastic regression imputation. Our model is a time-varying autoregression on the past innovations (residuals), and it can be used in cases where general dynamics must be taken into account, and where the model selection is important. The entire estimation process was carried out using available procedures in statistical packages such as SAS and S-PLUS. To illustrate the viability of the proposed model and the two-stage imputation method, we analyse data collected in an epidemiological study that focused on various factors relating to childhood growth. Finally, we present a simulation study to investigate the behaviour of our two-stage imputation procedure.",
keywords = "Incomplete data, Innovations sequence, Longitudinal analysis, Missing data, Multiple imputation, Stochastic regression imputation, Time-varying autoregression",
author = "Tulay Sengul and Stoffer, {David S.} and Day, {Nancy L.}",
year = "2007",
month = "7",
day = "30",
doi = "10.1002/sim.2757",
language = "English",
volume = "26",
pages = "3330--3341",
journal = "Statistics in Medicine",
issn = "0277-6715",
publisher = "John Wiley and Sons Ltd",
number = "17",

}

TY - JOUR

T1 - A residuals-based transition model for longitudinal analysis with estimation in the presence of missing data

AU - Sengul, Tulay

AU - Stoffer, David S.

AU - Day, Nancy L.

PY - 2007/7/30

Y1 - 2007/7/30

N2 - We propose a transition model for analysing data from complex longitudinal studies. Because missing values are practically unavoidable in large longitudinal studies, we also present a two-stage imputation method for handling general patterns of missing values on both the outcome and the covariates by combining multiple imputation with stochastic regression imputation. Our model is a time-varying autoregression on the past innovations (residuals), and it can be used in cases where general dynamics must be taken into account, and where the model selection is important. The entire estimation process was carried out using available procedures in statistical packages such as SAS and S-PLUS. To illustrate the viability of the proposed model and the two-stage imputation method, we analyse data collected in an epidemiological study that focused on various factors relating to childhood growth. Finally, we present a simulation study to investigate the behaviour of our two-stage imputation procedure.

AB - We propose a transition model for analysing data from complex longitudinal studies. Because missing values are practically unavoidable in large longitudinal studies, we also present a two-stage imputation method for handling general patterns of missing values on both the outcome and the covariates by combining multiple imputation with stochastic regression imputation. Our model is a time-varying autoregression on the past innovations (residuals), and it can be used in cases where general dynamics must be taken into account, and where the model selection is important. The entire estimation process was carried out using available procedures in statistical packages such as SAS and S-PLUS. To illustrate the viability of the proposed model and the two-stage imputation method, we analyse data collected in an epidemiological study that focused on various factors relating to childhood growth. Finally, we present a simulation study to investigate the behaviour of our two-stage imputation procedure.

KW - Incomplete data

KW - Innovations sequence

KW - Longitudinal analysis

KW - Missing data

KW - Multiple imputation

KW - Stochastic regression imputation

KW - Time-varying autoregression

UR - http://www.scopus.com/inward/record.url?scp=34447277399&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34447277399&partnerID=8YFLogxK

U2 - 10.1002/sim.2757

DO - 10.1002/sim.2757

M3 - Article

C2 - 17124699

AN - SCOPUS:34447277399

VL - 26

SP - 3330

EP - 3341

JO - Statistics in Medicine

JF - Statistics in Medicine

SN - 0277-6715

IS - 17

ER -