varComp (version 0.2-0)

varComp-package: Variance Component Models

Description

This package includes functions for fitting and testing variance component models, i.e., linear mixed-effect models with linear variance-covariance structures.

Details

Package:	varComp
Type:	Package
Version:	0.2-0
Date:	2017-07-09
License:	GPL3

• varComp: fitting variance component models.

• varComp.test: testing variance components.

• fixef.varComp: testing fixed-effect parameters by the Satterthwaite or Kenward-Roger method.

References

Qu L, Guennel T, Marshall SL. (2013) Linear Score Tests for Variance Components in Linear Mixed Models and Applications to Genetic Association Studies. Biometrics, Volume 69, Issue 4, pages 883--892.

See Also

nlme::lme

Examples

# NOT RUN {
### Oxide/Semiconductor example
library(nlme)
data(Oxide)
lmef = lme(Thickness~Source, Oxide, ~1|Lot/Wafer)
vcf = varComp(Thickness~Source, Oxide, ~Lot/Wafer)
VarCorr(lmef)
coef(vcf, 'varComp') ## same values as above

vcf0 = varComp(Thickness~1, Oxide, ~Lot/Wafer)
fixef(vcf)
anova(vcf, vcf0)
anova(vcf)
anova(vcf, L=diag(1,2)) ## notice the difference in the last row

### Genetics example	
trt=gl(2, 15)
set.seed(2340)
dat=data.frame(trt=trt)
dat$SNP=matrix(sample(0:2, 120, replace=TRUE), 30)
dat$Y  = as.numeric(trt)+rnorm(30) + dat$SNP%*%rnorm(4)
(vcf0 = varComp(Y~trt, dat, ~ibs(SNP)))
(vcf00 = varComp(Y~trt, dat, varcov = list(`ibs(SNP)`=IBS(dat$SNP)))) ## same as above
(vcf1 = varComp(Y~trt, dat, ~ibs(SNP):trt)) ## two variance components
summary(vcf0)

varComp.test(vcf0, vcf1)
varComp.test(vcf1, null=1)
varComp.test(Y~trt, dat, random1=~ibs(SNP), random2=~trt:ibs(SNP))


# }