2001
DOI: 10.1111/j.0006-341x.2001.00795.x
|View full text |Cite
|
Sign up to set email alerts
|

Linear Mixed Models with Flexible Distributions of Random Effects for Longitudinal Data

Abstract: Normality of random effects is a routine assumption for the linear mixed model, but it may be unrealistic, obscuring important features of among-individual variation. We relax this assumption by approximating the random effects density by the seminonparameteric (SNP) representation of Gallant and Nychka (1987, Econometrics 55, 363-390), which includes normality as a special case and provides flexibility in capturing a broad range of nonnormal behavior, controlled by a user-chosen tuning parameter. An advantage… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

14
299
0
4

Year Published

2006
2006
2017
2017

Publication Types

Select...
8
2

Relationship

1
9

Authors

Journals

citations
Cited by 263 publications
(317 citation statements)
references
References 16 publications
14
299
0
4
Order By: Relevance
“…Even then, however, mixture distributions are not the only answer. Other approaches for semiparametrically modeling the continuous (but not necessarily normal) distribution of the individual trajectories exist that do not resolve the population into artificial groups (e.g., Chen, Zhang, & Davidian, 2002;Zhang & Davidian, 2001).…”
Section: Groups That Do Not Existmentioning
confidence: 99%
“…Even then, however, mixture distributions are not the only answer. Other approaches for semiparametrically modeling the continuous (but not necessarily normal) distribution of the individual trajectories exist that do not resolve the population into artificial groups (e.g., Chen, Zhang, & Davidian, 2002;Zhang & Davidian, 2001).…”
Section: Groups That Do Not Existmentioning
confidence: 99%
“…where φ(·) is the standard normal density function, (ξ, η, a 0 , a 1 , a 2 ) are unknown parameters, and (a 0 , a 1 , a 2 ) are constrained so that (4) integrates to one (Zhang & Davidian, 2001). …”
Section: ·1 Full Latent-model Robustnessmentioning
confidence: 99%
“…There are, however, many other situations when the underlying distribution no longer satisfies the symmetric property (e.g., Zhang and Davidian [24]). Robust joint modeling can be found in Li et al [25] and Huang et al [26] where a student's t distribution in different structures of joint modeling of longitudinal and survival data is applied.…”
Section: Introductionmentioning
confidence: 99%