Score-based tests for detecting heterogeneity in linear mixed models

被引:0
作者
Ting Wang
Edgar C. Merkle
Joaquin A. Anguera
Brandon M. Turner
机构
[1] The American Board of Anesthesiology,
[2] University of Missouri,undefined
[3] University of California,undefined
[4] The Ohio State University,undefined
来源
Behavior Research Methods | 2021年 / 53卷
关键词
Score-based tests; Heterogeneity; Linear mixed models;
D O I
暂无
中图分类号
学科分类号
摘要
Cross-level interactions among fixed effects in linear mixed models (also known as multilevel models) can be complicated by heterogeneity stemming from random effects and residuals. When heterogeneity is present, tests of fixed effects (including cross-level interaction terms) are subject to inflated type I or type II error. While the impact of variance change/heterogeneity has been noticed in the literature, few methods have been proposed to detect this heterogeneity in a simple, systematic way. In addition, when heterogeneity among clusters is detected, researchers often wish to know which clusters’ variances differed from the others. In this study, we utilize a recently proposed family of score-based tests to distinguish between cross-level interactions and heterogeneity in variance components, also providing information about specific clusters that exhibit heterogeneity. These score-based tests only require estimation of the null model (when variance homogeneity is assumed to hold), and they have been previously applied to psychometric models to detect measurement invariance. In this paper, we extend the tests to linear mixed models, allowing us to use the tests to differentiate between interaction and heterogeneity. We detail the tests’ implementation and performance via simulation, provide an empirical example of the tests’ use in practice, and provide code illustrating the tests’ general application.
引用
收藏
页码:216 / 231
页数:15
相关论文
共 50 条
[11]   Detecting heterogeneity parameters and hybrid models for precision farming [J].
Ibidoja, Olayemi Joshua ;
Shan, Fam Pei ;
Sulaiman, Jumat ;
Ali, Majid Khan Majahar .
JOURNAL OF BIG DATA, 2023, 10 (01)
[12]   A Numerical Study of PQL Estimation Biases in Generalized Linear Mixed Models Under Heterogeneity of Random Effects [J].
Jang, Woncheol ;
Lim, Johan .
COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION, 2009, 38 (04) :692-702
[13]   Permutation tests for detecting treatment effect heterogeneity in cluster randomized trials [J].
Maleyeff, Lara ;
Li, Fan ;
Haneuse, Sebastien ;
Wang, Rui .
STATISTICAL METHODS IN MEDICAL RESEARCH, 2025,
[14]   Linear mixed models based on skew scale mixtures of normal distributions [J].
Ferreira, Clecio S. ;
Bolfarine, Heleno ;
Lachos, Victor H. .
COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION, 2022, 51 (12) :7194-7214
[15]   Leverage analysis for linear mixed models [J].
Nobre, Juvencio S. ;
Singer, Julio M. .
JOURNAL OF APPLIED STATISTICS, 2011, 38 (05) :1063-1072
[16]   Parallel computing in linear mixed models [J].
Yavuz, Fulya Gokalp ;
Schloerke, Barret .
COMPUTATIONAL STATISTICS, 2020, 35 (03) :1273-1289
[17]   Checking for normality in linear mixed models [J].
WU Ping ZHU LiXing FANG Yun School of Finance and StatisticsEast China Normal UniversityShanghai China School of Statistics and MathematicsYunnan University of Finance and EconomicsYunnan China The Department of MathematicsHong Kong Baptist UniversityHong Kong China Mathematics and Science CollegeShanghai Normal UniversityShanghai China .
ScienceChina(Mathematics), 2012, 55 (04) :782-799
[18]   Parallel computing in linear mixed models [J].
Fulya Gokalp Yavuz ;
Barret Schloerke .
Computational Statistics, 2020, 35 :1273-1289
[19]   Estimating moments in linear mixed models [J].
Wu, Ping ;
Fang, Yun ;
Zhu, Li-Xing .
COMMUNICATIONS IN STATISTICS-THEORY AND METHODS, 2008, 37 (16) :2582-2594
[20]   Checking for normality in linear mixed models [J].
Wu Ping ;
Zhu LiXing ;
Fang Yun .
SCIENCE CHINA-MATHEMATICS, 2012, 55 (04) :787-804