Adequacy of approximations to distributions of test statistics in complex mixed linear models

By G. B. Schaalje, J. McBride, G. Fellingham. 2002

294 citations recorded by the source corpus.

Subfields: Management Science and Operations Research, Plant Science, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/9336737e10ef993cfc873609562ee5358a9ee595

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 Plant Science

In Statistics and Probability

Citations in the corpus

Why You Should Always Include a Random Slope for the Lower-Level Variable Involved in a Cross-Level Interaction (2019, methodology): “If we applied the algorithm of Simonsohn et al. (2014) without further reflection, we would thus conclude that the reported findings have evidential basis and that there is no evidence of p-hacking, because all p-curves are significantly right skewed.”
Performance of the Kenward–Roger Method when the Covariance Structure is Selected Using AIC and BIC (2005, methodology): “For situations in which the covariance structure is known, small sample Type I error rates for the Wald F test using the SW and KR methods have been studied fairly extensively (Fai and Cornelius, 1996; Kenward and Roger, 1997; Schaalje et al., 2002).”
Interactive effects of tree and herb cover on survivorship, physiology, and microclimate of conifer seedlings at the alpine tree-line ecotone (2005, background): “ing F distributions because of our small sample size (Schaalje et al. 2002).”
A simulation study on tests of hypotheses and confidence intervals for fixed effects in mixed models for blocked experiments with missing data (2005, background): “Schaalje, McBride, and Fellingham (2002) investigated repeated-measures designs with five covariance structures.”
A Mixed Modelling Approach for Randomized Experiments with Repeated Measures (2004, methodology): “This has been shown to fare well in a number of settings, but more comprehensive simulation studies on the performance in small samples with repeated measures correlation structures are still needed before the method can be recommended for routine application (Schaalje et al. 2002).”
Evaluating significance in linear mixed-effects models in R (2016, background): “…and simple, single-factor models, so the observed Type 1 error rates might not hold up for a model with a more complex covariance structure (see Schaalje, McBride, & Fellingham, 2002, who show that the Kenward-Roger approximation, while generally robust, can lead to inflated Type 1 error rates…”
lmerTest Package: Tests in Linear Mixed Effects Models (2017, background): “Schaalje, McBride, and Fellingham (2002) performed a number of simulations in order to investigate the appropriateness of the approximation methods.”