Misspecifying the Shape of a Random Effects Distribution: Why Getting It Wrong May Not Matter

By Charles E. McCulloch, J. Neuhaus. 2011

234 citations recorded by the source corpus.

Statistical models that include random effects are commonly used to analyze longitudinal and correlated data, often with strong and parametric assumptions about the random effects distribution. There is marked disagreement in the literature as to whether such parametric assumptions are important or innocuous. In the context of generalized linear mixed models used to analyze clustered or longitudinal data, we examine the impact of random effects distribution misspecification on a variety of inferences, including prediction, inference about covariate effects, prediction of random effects and estimation of random effects variances. We describe examples, theoretical calculations and simulations to elucidate situations in which the specification is and is not important. A key conclusion is the large degree of robustness of maximum likelihood for a wide variety of commonly encountered situations.

Subfields: Artificial Intelligence, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/cec775be96a4cedc1982a58ff1b3b07cf33aa214

How researchers see this paper

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

In Artificial Intelligence

In Statistics and Probability

Citations in the corpus

Robustness of linear mixed‐effects models to violations of distributional assumptions (2020, background): “Unfortunately, very few studies have assessed random effect variances and predictions (e.g. Maas & Hox, 2004; McCulloch & Neuhaus, 2011; Verbeke & Lesaffre, 1996); for those who did, the estimation of the group variance is usually accurate, but random effect coefficients (best linear unbiased…”
Intermediate and advanced topics in multilevel logistic regression analysis (2017, background): “In terms of estimating the variance of the random effects distribution, McCulloch and Neuhaus suggest that ‘estimation of the random effects variance appears relatively robust to misspecification of the random intercept distributional shape’ [46] (page 395).”