A simple test for random effects in regression models

By Simon N. Wood. 2013

126 citations recorded by the source corpus.

Testing that random effects are zero is difficult, because the null hypothesis restricts the corresponding variance parameter to the edge of the feasible parameter space. In the context of generalized linear mixed models, this paper exploits the link between random effects and penalized regression to develop a simple test for a zero effect. The idea is to treat the variance components not being tested as fixed at their estimates and then to express the likelihood ratio as a readily computed quadratic form in the predicted values of the random effects. Under the null hypothesis this has the distribution of a weighted sum of squares of independent standard normal random variables. The test can be used with generalized linear mixed models, including those estimated by penalized quasilikelihood. Copyright 2013, Oxford University Press.

Subfields: Management Science and Operations Research, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/400c1ad62b8a8480a202f34a007c8f7c66647ceb

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Management Science and Operations Research

In Statistics and Probability

Citations in the corpus

The cave of Shadows. Addressing the human factor with generalized additive mixed models (2015, methodology): “The p-values listed in these tables for the smooth terms are based on specific F ratios that are discussed in detail in Wood (2013a) for regression splines and in Wood (2013b) for random effects.”
A general framework for functional regression modelling (2017, methodology): “…of this approach is the availability of CIs and tests using mixed model-based likelihood inference methodology (e.g., Marra and Wood, 2012; Wood, 2013), with close to nominal CI coverages for (generalized) functional responses on simulated data (Ivanescu et al., 2015; Scheipl et al.,…”
Aperiodic EEG and 7T MRSI evidence for maturation of E/I balance supporting the development of working memory through adolescence (2024, methodology): “Regression splines were implemented (4 degrees of freedom) to assess linear and non-linear effects (Wood, 2017, 2013).”