Description
summary.asreml is a summary method for objects inheriting from class asreml
.
Usage
## S3 method for class 'asreml' summary(object, param = c("sigma", "gamma"), coef = FALSE, vparameters = FALSE, ...)
Arguments
object 
An asreml object. 
param 
If “sigma ” (the default), random parameter values are reported on the sigma scale only, otherwise, if “gamma “, an additional column of variance ratios is returned. 
coef 
If TRUE (default is FALSE ), the coefficients and their standard errors are included in the return object. 
vparameters 
If TRUE (default is FALSE ), the variance parameters are included in the return object in list form. 
... 
Additional arguments. 
Value
A list of class summary.asreml with the following components: 

call 
The call component from object 
loglik 
The loglik component from object 
nedf 
The nedf component from object . 
sigma 
sqrt(object\$sigma2). 
varcomp 
A dataframe summarising the random parameter vector (object$vparameters) . Variance component ratios are included if param="gamma" , and a measure of precision is included along with boundary constraints at termination and the percentage change in the final iteration. 
aic 
Akaike information criterion. 
bic 
Bayesian information criterion. 
distribution 
A character string identifying the error distribution(s) if object$deviance != 0 . 
link 
A character string identifying the link function(s) if object$deviance != 0 . 
deviance 
The deviance from the fit if object$deviance != 0 . 
heterogeneity 
Variance heterogeneity (deviance/nedf) if object$deviance != 0 . 
coef.fixed 
A matrix of coefficients and their standard errors for fixed effects if coef=TRUE . 
coef.random 
A matrix of coefficients and their standard errors for random effects if coef=TRUE . 
coef.sparse 
A matrix of coefficients and their standard errors for sparsefixed effects if coef=TRUE . 
vparameters 
A list of variance structures with matrices converted to full dense form. For ante and chol models the components are given in varcomp and returned in gammas in variancecovariance form. 