Sensitivity analysis of mixed models for incomplete longitudinal data

Violet Shu Xu, Shelley A. Blozis

Research output: Contribution to journalArticle

Abstract

Mixed models are used for the analysis of data measured over time to study population-level change and individual differences in change characteristics. Linear and nonlinear functions may be used to describe a longitudinal response, individuals need not be observed at the same time points, and missing data, assumed to be missing at random (MAR), may be handled. While the mechanism giving rise to the missing data cannot be determined by the observations, the sensitivity of parameter estimates to missing data assumptions can be studied, for example, by fitting multiple models that make different assumptions about the missing data process. Sensitivity analysis of a mixed model that may include nonlinear parameters when some data are missing is discussed. An example is provided.

Original languageEnglish (US)
Pages (from-to)237-256
Number of pages20
JournalJournal of Educational and Behavioral Statistics
Volume36
Issue number2
DOIs
StatePublished - Jun 1 2011

Fingerprint

demographic situation
time

Keywords

  • data analysis
  • hierarchical modeling
  • longitudinal studies

ASJC Scopus subject areas

  • Education
  • Social Sciences (miscellaneous)

Cite this

Sensitivity analysis of mixed models for incomplete longitudinal data. / Xu, Violet Shu; Blozis, Shelley A.

In: Journal of Educational and Behavioral Statistics, Vol. 36, No. 2, 01.06.2011, p. 237-256.

Research output: Contribution to journalArticle

@article{43621c6a9a1b48ddb2469c7aa2eb9d85,
title = "Sensitivity analysis of mixed models for incomplete longitudinal data",
abstract = "Mixed models are used for the analysis of data measured over time to study population-level change and individual differences in change characteristics. Linear and nonlinear functions may be used to describe a longitudinal response, individuals need not be observed at the same time points, and missing data, assumed to be missing at random (MAR), may be handled. While the mechanism giving rise to the missing data cannot be determined by the observations, the sensitivity of parameter estimates to missing data assumptions can be studied, for example, by fitting multiple models that make different assumptions about the missing data process. Sensitivity analysis of a mixed model that may include nonlinear parameters when some data are missing is discussed. An example is provided.",
keywords = "data analysis, hierarchical modeling, longitudinal studies",
author = "Xu, {Violet Shu} and Blozis, {Shelley A.}",
year = "2011",
month = "6",
day = "1",
doi = "10.3102/1076998610375836",
language = "English (US)",
volume = "36",
pages = "237--256",
journal = "Journal of Educational and Behavioral Statistics",
issn = "1076-9986",
publisher = "SAGE Publications Inc.",
number = "2",

}

TY - JOUR

T1 - Sensitivity analysis of mixed models for incomplete longitudinal data

AU - Xu, Violet Shu

AU - Blozis, Shelley A.

PY - 2011/6/1

Y1 - 2011/6/1

N2 - Mixed models are used for the analysis of data measured over time to study population-level change and individual differences in change characteristics. Linear and nonlinear functions may be used to describe a longitudinal response, individuals need not be observed at the same time points, and missing data, assumed to be missing at random (MAR), may be handled. While the mechanism giving rise to the missing data cannot be determined by the observations, the sensitivity of parameter estimates to missing data assumptions can be studied, for example, by fitting multiple models that make different assumptions about the missing data process. Sensitivity analysis of a mixed model that may include nonlinear parameters when some data are missing is discussed. An example is provided.

AB - Mixed models are used for the analysis of data measured over time to study population-level change and individual differences in change characteristics. Linear and nonlinear functions may be used to describe a longitudinal response, individuals need not be observed at the same time points, and missing data, assumed to be missing at random (MAR), may be handled. While the mechanism giving rise to the missing data cannot be determined by the observations, the sensitivity of parameter estimates to missing data assumptions can be studied, for example, by fitting multiple models that make different assumptions about the missing data process. Sensitivity analysis of a mixed model that may include nonlinear parameters when some data are missing is discussed. An example is provided.

KW - data analysis

KW - hierarchical modeling

KW - longitudinal studies

UR - http://www.scopus.com/inward/record.url?scp=79955069622&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79955069622&partnerID=8YFLogxK

U2 - 10.3102/1076998610375836

DO - 10.3102/1076998610375836

M3 - Article

VL - 36

SP - 237

EP - 256

JO - Journal of Educational and Behavioral Statistics

JF - Journal of Educational and Behavioral Statistics

SN - 1076-9986

IS - 2

ER -