gremlin (version 0.1.0.1)

gremlin-package: Mixed-Effects REML Incorporating Generalized Inverses

Description

Fit linear mixed-effects models using restricted (or residual) maximum likelihood (REML) and with generalized inverse matrices to specify covariance structures for random effects. In particular, the package is suited to fit quantitative genetic mixed models, often referred to as 'animal models' (Kruuk 2004 <DOI: 10.1098/rstb.2003.1437>). Implements the average information algorithm as the main tool to maximize the restricted likelihood, but with other algorithms available (Meyer. 1997. Genet Sel Evol 29:97; Meyer & Smith. 1998. Genet Sel Evol 28:23.).

Details

The package also implements the average information algorithm to efficiently maximize the log-likelihood (Thompson & Johnson 1995; Gilmour et al. 1995; Meyer & Smith 1996). The average information algorithm combined with sparse matrix techniques can potentially make model fitting very efficient.

References

Mrode, RA. 2005. Linear Models for the Prediction of Animal Breeding Values, 2nd ed. CABI Publishing, Cambridge. Meyer, K & Smith, SP. 1996. Restricted maximum likelihood estimation for animal models using derivatives of the likelihood. Genetics Selection Evolution 28:23-49. Gilmour, AR, Thompson, R, & Cullis, BR. 1995. Average information REML: An efficient algorithm for variance parameter estimation in linear mixed models. Biometrics 51:1440-1450. Johnson, DL, & Thompson, R. 1995. Restricted maximum likelihood estimation of variance components for univariate animal models using sparse matrix techniques and average information. Journal of Dairy Science 78:449-456.

See Also

MCMCglmm

Examples

# NOT RUN {
  require(nadiv)
  Ainv <- makeAinv(Mrode3[-c(1:2), 1:3])$Ainv
  mod11 <- gremlinR(WWG11 ~ sex - 1,
random = ~ calf,
data = Mrode11,
ginverse = list(calf = Ainv),
Gstart = matrix(0.2), Rstart = matrix(0.4),
maxit = 10, v = 2)
# }