In this paper, we develop a simple diagnostic test for the random-effects distribution in mixed models. The test is based on the gradient function, a graphical tool proposed by Verbeke and Molenberghs to check the impact of assumptions about the random-effects distribution in mixed models on inferences. Inference is conducted through the bootstrap. The proposed test is easy to implement and applicable in a general class of mixed models. The operating characteristics of the test are evaluated in a simulation study, and the method is further illustrated using two real data analyses.
VerbekeGMolenberghsG. Linear mixed models for longitudinal data, New York: Springer, 2000.
2.
MolenberghsGVerbekeG. Models for discrete longitudinal data, New York: Springer, 2005.
3.
NeuhausJMHauckWWKalbfleischJD. The effects of mixture distribution specification when fitting mixed-effects logistic models. Biometrika1992; 79: 755–762.
4.
VerbekeGLesaffreE. The effect of misspecifying the random-effects distribution in linear mixed models for longitudinal data. Comput Stat Data Anal1997; 23: 542–556.
5.
McCullochCENeuhausJM. Misspecifying the shape of a random-effects distribution: why getting it wrong may not matter. Stat Sci2011; 26(3): 388–402.
6.
HeagertyPJZegerSL. Marginalized multilevel models and likelihood inference. Stat Sci2000; 15(1): 1–26.
7.
HeagertyPJKurlandBF. Misspecified maximum likelihood estimates and generalised linear mixed models. Biometrika2001; 88(4): 973–985.
8.
AgrestiACaffoBOhman-StricklandP. Examples in which misspecification of random-effects distribution reduces efficiency, and possible remedies. Comput Stat Data Anal2004; 47: 639–653.
9.
LitièreSAlonsoAMolenberghsG. The impact of a misspecified random-effects distribution on the estimation and the performance of inferential procedures in generalized linear mixed model. Stat Med2008; 27: 3125–3144.
10.
TsonakaRVerbekeGLesaffreE. A semi-parametric shared parameter model to handle nonmonotone nonignorable missingness. Biometrics2009; 65: 81–87.
11.
GhideyWLesaffreEVerbekeG. A comparison of methods for estimating the random-effects distribution of a linear mixed model. Stat Methods Med Res2010; 19: 575–600.
12.
VerbekeGMolenberghsG. The gradient function as an exploratory goodness-of-fit assessment of the random-effects distribution in mixed models. Biostatistics2013; 14(3): 477–490.
PanZLinDY. Goodness-of-fit methods for generalized linear mixed models. Biometrics2005; 61: 1000–1009.
15.
TchetgenEJCoullBA. A diagnostic test for the mixing distribution in a generalized linear mixed model. Biometrika2006; 93: 1003–1010.
16.
HuangX. Diagnosis of random-effect model misspecification in generalized linear mixed models for binary response. Biometrics2009; 65: 361–368.
17.
AlonsoALitièreSMolenberghsG. A family of tests to detect misspecifications in the random-effects structure of generalized linear mixed models. Comput Stat Data Anal2008; 52: 4474–4486.
18.
AlonsoALitièreSMolenberghsG. Testing for misspecifications in generalized linear mixed models. Biostatistics2010; 11(4): 771–786.
19.
RobertsDT. Prevalence of dermatophyte onychomicosis in the United Kingdom: results of an omnibus survey. Br J Dermatol1992; 126(Suppl 39): 23–27.
20.
De BackerMDe KeyserPDe VroeyC, et al.A 12-week treatment for dermatophyte toe onychomycosis: terninafine 250 mg/day vs. itraconazole 200 mg/day - a double-blind comparative trial. Br J Dermatol1996; 143: 16–17.
21.
FaughtEWilderBJRamsayRE, et al.Topiramate placebo-controlled dose-ranging trial in refractory partial epilepsy using 200-, 400-, and 600-mg daily dosage. Neurology1996; 46: 1684–1690.
22.
VerbekeGLesaffreE. A linear mixed-effects model with heterogeneity in the random effects population. J Am Stat Assoc1996; 91: 217–221.
23.
MolenberghsGVerbekeGDemétrioC, et al.A family of generalized linear models for repeated measures with normal and conjugate random effects. Stat Sci2010; 5: 325–347.
