On the inefficiency of the restricted maximum likelihood
N. T. Longford
Abstract
The restricted maximum likelihood is preferred by many to the full maximum
likelihood in estimation with variance component and other random coefficient
models, because the variance estimator is unbiased.
It is shown that this unbiasedness is accompanied by an inflation
of the mean squared error in the balanced one-way analysis of variance
and an estimator that is uniformly more efficient than full maximum likelihood
is derived.
In Statistica Neerlandica 69, 171-196, 2015.