Approaches for Specifying the Level-1 Error Structure When Synthesizing Single-Case Data

Seang Hwane Joo, John M. Ferron, Mariola Moeyaert, S Natasha Beretvas, Wim Van den Noortgate

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Multilevel modeling has been utilized for combining single-case experimental design (SCED) data assuming simple level-1 error structures. The purpose of this study is to compare various multilevel analysis approaches for handling potential complexity in the level-1 error structure within SCED data, including approaches assuming simple and complex error structures (heterogeneous, autocorrelation, and both) and those using fit indices to select between alternative error structures. A Monte Carlo study was conducted to empirically validate the suggested multilevel modeling approaches. Results indicate that each approach leads to fixed effect estimates with little to no bias and that inferences for fixed effects were frequently accurate, particularly when a simple homogeneous level-1 error structure or a first-order autoregressive structure was assumed and the inferences were based on the Kenward-Roger method. Practical implications and recommendations are discussed.

Original languageEnglish (US)
Pages (from-to)55-74
Number of pages20
JournalJournal of Experimental Education
Volume87
Issue number1
DOIs
StatePublished - Jan 2 2019

Fingerprint

Research Design
Multilevel Analysis
multi-level analysis
trend

Keywords

  • Heterogeneous variance
  • Monte Carlo study
  • model specification
  • multilevel modeling
  • single-case experimental design

ASJC Scopus subject areas

  • Education
  • Developmental and Educational Psychology

Cite this

Approaches for Specifying the Level-1 Error Structure When Synthesizing Single-Case Data. / Joo, Seang Hwane; Ferron, John M.; Moeyaert, Mariola; Beretvas, S Natasha; Van den Noortgate, Wim.

In: Journal of Experimental Education, Vol. 87, No. 1, 02.01.2019, p. 55-74.

Research output: Contribution to journalArticle

Joo, Seang Hwane ; Ferron, John M. ; Moeyaert, Mariola ; Beretvas, S Natasha ; Van den Noortgate, Wim. / Approaches for Specifying the Level-1 Error Structure When Synthesizing Single-Case Data. In: Journal of Experimental Education. 2019 ; Vol. 87, No. 1. pp. 55-74.
@article{6f92c9343a0b49388b7d13a160f7275e,
title = "Approaches for Specifying the Level-1 Error Structure When Synthesizing Single-Case Data",
abstract = "Multilevel modeling has been utilized for combining single-case experimental design (SCED) data assuming simple level-1 error structures. The purpose of this study is to compare various multilevel analysis approaches for handling potential complexity in the level-1 error structure within SCED data, including approaches assuming simple and complex error structures (heterogeneous, autocorrelation, and both) and those using fit indices to select between alternative error structures. A Monte Carlo study was conducted to empirically validate the suggested multilevel modeling approaches. Results indicate that each approach leads to fixed effect estimates with little to no bias and that inferences for fixed effects were frequently accurate, particularly when a simple homogeneous level-1 error structure or a first-order autoregressive structure was assumed and the inferences were based on the Kenward-Roger method. Practical implications and recommendations are discussed.",
keywords = "Heterogeneous variance, Monte Carlo study, model specification, multilevel modeling, single-case experimental design",
author = "Joo, {Seang Hwane} and Ferron, {John M.} and Mariola Moeyaert and Beretvas, {S Natasha} and {Van den Noortgate}, Wim",
year = "2019",
month = "1",
day = "2",
doi = "10.1080/00220973.2017.1409181",
language = "English (US)",
volume = "87",
pages = "55--74",
journal = "Journal of Experimental Education",
issn = "0022-0973",
publisher = "Routledge",
number = "1",

}

TY - JOUR

T1 - Approaches for Specifying the Level-1 Error Structure When Synthesizing Single-Case Data

AU - Joo, Seang Hwane

AU - Ferron, John M.

AU - Moeyaert, Mariola

AU - Beretvas, S Natasha

AU - Van den Noortgate, Wim

PY - 2019/1/2

Y1 - 2019/1/2

N2 - Multilevel modeling has been utilized for combining single-case experimental design (SCED) data assuming simple level-1 error structures. The purpose of this study is to compare various multilevel analysis approaches for handling potential complexity in the level-1 error structure within SCED data, including approaches assuming simple and complex error structures (heterogeneous, autocorrelation, and both) and those using fit indices to select between alternative error structures. A Monte Carlo study was conducted to empirically validate the suggested multilevel modeling approaches. Results indicate that each approach leads to fixed effect estimates with little to no bias and that inferences for fixed effects were frequently accurate, particularly when a simple homogeneous level-1 error structure or a first-order autoregressive structure was assumed and the inferences were based on the Kenward-Roger method. Practical implications and recommendations are discussed.

AB - Multilevel modeling has been utilized for combining single-case experimental design (SCED) data assuming simple level-1 error structures. The purpose of this study is to compare various multilevel analysis approaches for handling potential complexity in the level-1 error structure within SCED data, including approaches assuming simple and complex error structures (heterogeneous, autocorrelation, and both) and those using fit indices to select between alternative error structures. A Monte Carlo study was conducted to empirically validate the suggested multilevel modeling approaches. Results indicate that each approach leads to fixed effect estimates with little to no bias and that inferences for fixed effects were frequently accurate, particularly when a simple homogeneous level-1 error structure or a first-order autoregressive structure was assumed and the inferences were based on the Kenward-Roger method. Practical implications and recommendations are discussed.

KW - Heterogeneous variance

KW - Monte Carlo study

KW - model specification

KW - multilevel modeling

KW - single-case experimental design

UR - http://www.scopus.com/inward/record.url?scp=85039057696&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85039057696&partnerID=8YFLogxK

U2 - 10.1080/00220973.2017.1409181

DO - 10.1080/00220973.2017.1409181

M3 - Article

VL - 87

SP - 55

EP - 74

JO - Journal of Experimental Education

JF - Journal of Experimental Education

SN - 0022-0973

IS - 1

ER -