Structural multivariate-univariate linear mixed model solver for estimation of multiple random effects and unknown variance-covariance structures (i.e. heterogeneous and unstructured variance models) (Covarrubias-Pazaran, 2016; Maier et al., 2015). REML estimates can be obtained using the Direct-Inversion Newton-Raphson and Direct-Inversion Average Information algorithms. Designed for genomic prediction and genome wide association studies (GWAS), particularly focused in the p > n problem (more coefficients than observations) and dense known covariance structures for levels of random effects. Spatial models can also be fitted using i.e. the two-dimensional spline functionality available in sommer.
You can install the development version of sommer
from GitHub:
devtools::install_github('covaruber/sommer')
- Quick start for the sommer package
- Moving to newer versions of sommer
- Quantitative genetics using the sommer package
- GxE models in sommer
- lme4 vs sommer
The sommer package is under active development. If you are an expert in mixed models, statistics or programming and you know how to implement of the following:
- the minimum degree ordering algorithm
- the symbolic cholesky factorization
- factor analytic structure
- generalized linear models
please help us to take sommer to the next level. Drop me an email or push some changes through github :)