R package for mixed-effects model REML incorporating Generalized Inverses (so, with some mental gymnastics: GREMLIN).

See the latest developments:

Overview of main branches:

To install gremlin:

# Install master branch install_github(“matthewwolak/gremlin”)

# Install devel branch install_github(“matthewwolak/gremlin”, ref = “devel”) ```


library(nadiv)  #<-- needed for creating inverse relatedness matrices

# Set up a subset of data for the example
warcolak$IDD <- warcolak$ID

# Create generalized inverse matrices
Ainv <- makeAinv(warcolak[, 1:3])$Ainv
Dinv <- makeD(warcolak[, 1:3])$Dinv

# Basic model structure is as follows:
## Fixed effects of sex
## ID  = autosomal additive genetic variance term
## IDD = autosomal dominance genetic variance term
grAD <- gremlin(trait1 ~ sex-1,
    random = ~ ID + IDD,
    ginverse = list(ID = Ainv, IDD = Dinv),
    data = warcolak)

# Summary