REML likelihood ratio test (REMLRT)

Description

This function extracts the REML log-likelihood values and numbers of variance parameters from a sequence of asreml objects to compute a sequence of pairwise REML likelihood ratio tests. It uses the asymptotic chi-square distribution of the REMLRT statistic.

Usage

## S3 method for class 'asreml'
lrt(..., boundary = TRUE)

Arguments

Details

The REMLRT is only valid if the fixed effects are the same for both models. This requires not only the same fixed effects model, but also the same parameterisation. The models are arranged in increasing order of number of variance parameters and they are assumed to be nested in this sequence.

If the reduced model is obtained by setting positively-constrained variance parameters in the full model to zero, set boundary = TRUE. In this case the probability is computed using a mixture of chi-square distributions as described in Self and Liang (1987).

Value

A data frame with a row for each successive pairwise test, and columns for the REML likelihood ratio statistic, degrees of freedom and number of parameters.