Data Transforming Augmentation for Linear Mixed Models

We provide a toolbox to fit univariate and multivariate linear mixed models via data transforming augmentation. Users can also fit these models via typical data augmentation for a comparison. It returns either maximum likelihood estimates of unknown model parameters (hyper-parameters) via an EM algorithm or posterior samples of those parameters via MCMC. Also see Tak et al. (2019) .

Penalized Linear Mixed Models for Correlated Data

Fits penalized linear mixed models that correct for unobserved confounding factors. 'plmmr' infers and corrects for the presence of unobserved confounding effects such as population stratification and environmental heterogeneity. It then fits a linear model via penalized maximum likelihood. Originally designed for the multivariate analysis of single nucleotide polymorphisms (SNPs) measured in a genome-wide association study (GWAS), 'plmmr' eliminates the need for subpopulation-specific analyses and post-analysis p-value adjustments. Functions for the appropriate processing of 'PLINK' files are also supplied. For examples, see the package homepage. < https://pbreheny.github.io/plmmr/>.

Bayesian Mixed Models for Qualitative Individual Differences

Test whether equality and order constraints hold for all individuals simultaneously by comparing Bayesian mixed models through Bayes factors. A tutorial style vignette and a quickstart guide are available, via vignette("manual", "quid"), and vignette("quickstart", "quid") respectively. See Haaf and Rouder (2017) ; Haaf, Klaassen and Rouder (2019) ; and Rouder & Haaf (2021) .

Bayesian Longitudinal Regularized Quantile Mixed Model

In longitudinal studies, the same subjects are measured repeatedly over time, leading to correlations among the repeated measurements. Properly accounting for the intra-cluster correlations in the presence of data heterogeneity and long tailed distributions of the disease phenotype is challenging, especially in the context of high dimensional regressions. In this package, we developed a Bayesian quantile mixed effects model with spike- and -slab priors to dissect important gene - environment interactions under longitudinal genomics studies. An efficient Gibbs sampler has been developed to facilitate fast computation. The Markov chain Monte Carlo algorithms of the proposed and alternative methods are efficiently implemented in 'C++'. The development of this software package and the associated statistical methods have been partially supported by an Innovative Research Award from Johnson Cancer Research Center, Kansas State University.

Multiplicative Mixed Models using the Template Model Builder

Fit multiplicative mixed models using maximum likelihood estimation via the Template Model Builder (TMB), Kristensen K, Nielsen A, Berg CW, Skaug H, Bell BM (2016) . One version of the multiplicative mixed model is applied in Piepho (1999) . The package provides functions for calculating confidence intervals for the model parameters and for performing likelihood ratio tests.

Bayesian Model Selection for Generalized Linear Mixed Models

A Bayesian model selection approach for generalized linear mixed models. Currently, 'GLMMselect' can be used for Poisson GLMM and Bernoulli GLMM. 'GLMMselect' can select fixed effects and random effects simultaneously. Covariance structures for the random effects are a product of a unknown scalar and a known semi-positive definite matrix. 'GLMMselect' can be widely used in areas such as longitudinal studies, genome-wide association studies, and spatial statistics. 'GLMMselect' is based on Xu, Ferreira, Porter, and Franck (202X), Bayesian Model Selection Method for Generalized Linear Mixed Models, Biometrics, under review.

Graphical Markov Models with Mixed Graphs

Provides functions for defining mixed graphs containing three types of edges, directed, undirected and bi-directed, with possibly multiple edges. These graphs are useful because they capture fundamental independence structures in multivariate distributions and in the induced distributions after marginalization and conditioning. The package is especially concerned with Gaussian graphical models for (i) ML estimation for directed acyclic graphs, undirected and bi-directed graphs and ancestral graph models (ii) testing several conditional independencies (iii) checking global identification of DAG Gaussian models with one latent variable (iv) testing Markov equivalences and generating Markov equivalent graphs of specific types.

Automated Estimation of Sigmoidal and Piecewise Linear Mixed Models

Estimation of relatively complex nonlinear mixed-effects models, including the Sigmoidal Mixed Model and the Piecewise Linear Mixed Model with abrupt or smooth transition, through a single intuitive line of code and with automated generation of starting values.

Learning and Communicating Linear Mixed Models Without Data

Summarizes characteristics of linear mixed effects models without data or a fitted model by converting code for fitting lmer() from 'lme4' and lme() from 'nlme' into tables, equations, and visuals. Outputs can be used to learn how to fit linear mixed effects models in 'R' and to communicate about these models in presentations, manuscripts, and analysis plans.

Linear Mixed Models - An Introduction with Applications in Veterinary Research

R Codes and Datasets for Duchateau, L. and Janssen, P. and Rowlands, G. J. (1998). Linear Mixed Models. An Introduction with applications in Veterinary Research. International Livestock Research Institute.