aiCI: Confidence Intervals for Variance Components

In matthewwolak/nadiv: (Non)Additive Genetic Relatedness Matrices

Confidence Intervals for Variance Components

Description

Produces the 1-alpha Upper and Lower Confidence Limits for the variance components in an ASReml-R model.

Usage

aiCI(asr.model, Dimnames = NULL, alpha = 0.05)

Arguments

asr.model	Object from a call to asreml
Dimnames	A vector of characters if names are desired for the output. If not specified, the default labels from the asreml object will be used.
alpha	A numeric value indicating the level of Type I error for constructing the Confidence Intervals.

Details

Variances from the inverse of the Average Information matrix of an ASReml model are translated according to the varTrans function and used in constructing the 1-alpha Confidence Interval.

Value

A matrix is returned with a row for each variance component. The three columns correspond to the Lower Confidence Limit, estimate from the asreml model, and Upper Confidence Limit for each variance component.

Note

The vector of Dimnames should match the same order of variance components specified in the model.

Author(s)

[e-mail]

See Also

aiFun proLik

Examples

  ## Not run: 
    library(asreml)
    ginvA <- asreml.Ainverse(warcolak)$ginv
    ginvD <- makeD(warcolak[,1:3])$listDinv
    warcolak$IDD <- warcolak$ID
    warcolak.mod <- asreml(trait1 ~ sex, random = ~ped(ID) + giv(IDD), 
	ginverse = list(ID = ginvA, IDD = ginvD), data = warcolak) 
    summary(warcolak.mod)$varcomp
    aiCI(warcolak.mod)    
   
## End(Not run)

matthewwolak/nadiv documentation built on July 7, 2023, 1:24 p.m.