Evaluating supplemental samples in longitudinal research: Replacement and refreshment approaches

Laura K. Taylor, Xin Tong, Scott E. Maxwell

Research output: Contribution to journalArticle

Abstract

Despite the wide application of longitudinal studies, they are often plagued by missing data and attrition. The majority of methodological approaches focus on participant retention or modern missing data analysis procedures. This paper, however, takes a new approach by examining how researchers may supplement the sample with additional participants. First, refreshment samples use the same selection criteria as the initial study. Second, replacement samples identify auxiliary variables that may help explain patterns of missingness, and select new participants based on those characteristics. A simulation study compares these two strategies for a linear growth model with five measurement occasions. Overall, the results suggest that refreshment samples lead to less relative bias, greater relative efficiency, and more acceptable coverage rates than replacement samples or not supplementing the missing participants in any way. Refreshment samples also have high statistical power. The comparative strengths of the refreshment approach are further illustrated through a real data example. These findings have implications for assessing change over time when researching at-risk samples with high levels of permanent attrition.
Original languageEnglish
Number of pages23
JournalMultivariate Behavioral Research
Early online date02 Jul 2019
DOIs
Publication statusEarly online date - 02 Jul 2019

Fingerprint

analysis procedure
supplement
longitudinal study
data analysis
coverage
efficiency
simulation
trend
time

Keywords

  • planned missing data
  • supplemental sample
  • replacement sample
  • refreshment sample
  • longitudinal design

Cite this

@article{0296c1044f2241469c6ed55129f2282d,
title = "Evaluating supplemental samples in longitudinal research: Replacement and refreshment approaches",
abstract = "Despite the wide application of longitudinal studies, they are often plagued by missing data and attrition. The majority of methodological approaches focus on participant retention or modern missing data analysis procedures. This paper, however, takes a new approach by examining how researchers may supplement the sample with additional participants. First, refreshment samples use the same selection criteria as the initial study. Second, replacement samples identify auxiliary variables that may help explain patterns of missingness, and select new participants based on those characteristics. A simulation study compares these two strategies for a linear growth model with five measurement occasions. Overall, the results suggest that refreshment samples lead to less relative bias, greater relative efficiency, and more acceptable coverage rates than replacement samples or not supplementing the missing participants in any way. Refreshment samples also have high statistical power. The comparative strengths of the refreshment approach are further illustrated through a real data example. These findings have implications for assessing change over time when researching at-risk samples with high levels of permanent attrition.",
keywords = "planned missing data, supplemental sample, replacement sample, refreshment sample, longitudinal design",
author = "Taylor, {Laura K.} and Xin Tong and Maxwell, {Scott E.}",
year = "2019",
month = "7",
day = "2",
doi = "10.1080/00273171.2019.1628694",
language = "English",
journal = "Multivariate Behavioral Research",
issn = "0027-3171",
publisher = "Taylor & Francis",

}

Evaluating supplemental samples in longitudinal research: Replacement and refreshment approaches. / Taylor, Laura K.; Tong, Xin; Maxwell, Scott E.

In: Multivariate Behavioral Research, 02.07.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Evaluating supplemental samples in longitudinal research: Replacement and refreshment approaches

AU - Taylor, Laura K.

AU - Tong, Xin

AU - Maxwell, Scott E.

PY - 2019/7/2

Y1 - 2019/7/2

N2 - Despite the wide application of longitudinal studies, they are often plagued by missing data and attrition. The majority of methodological approaches focus on participant retention or modern missing data analysis procedures. This paper, however, takes a new approach by examining how researchers may supplement the sample with additional participants. First, refreshment samples use the same selection criteria as the initial study. Second, replacement samples identify auxiliary variables that may help explain patterns of missingness, and select new participants based on those characteristics. A simulation study compares these two strategies for a linear growth model with five measurement occasions. Overall, the results suggest that refreshment samples lead to less relative bias, greater relative efficiency, and more acceptable coverage rates than replacement samples or not supplementing the missing participants in any way. Refreshment samples also have high statistical power. The comparative strengths of the refreshment approach are further illustrated through a real data example. These findings have implications for assessing change over time when researching at-risk samples with high levels of permanent attrition.

AB - Despite the wide application of longitudinal studies, they are often plagued by missing data and attrition. The majority of methodological approaches focus on participant retention or modern missing data analysis procedures. This paper, however, takes a new approach by examining how researchers may supplement the sample with additional participants. First, refreshment samples use the same selection criteria as the initial study. Second, replacement samples identify auxiliary variables that may help explain patterns of missingness, and select new participants based on those characteristics. A simulation study compares these two strategies for a linear growth model with five measurement occasions. Overall, the results suggest that refreshment samples lead to less relative bias, greater relative efficiency, and more acceptable coverage rates than replacement samples or not supplementing the missing participants in any way. Refreshment samples also have high statistical power. The comparative strengths of the refreshment approach are further illustrated through a real data example. These findings have implications for assessing change over time when researching at-risk samples with high levels of permanent attrition.

KW - planned missing data

KW - supplemental sample

KW - replacement sample

KW - refreshment sample

KW - longitudinal design

U2 - 10.1080/00273171.2019.1628694

DO - 10.1080/00273171.2019.1628694

M3 - Article

JO - Multivariate Behavioral Research

JF - Multivariate Behavioral Research

SN - 0027-3171

ER -