In the paper the problem of testing hypotheses for variance components
in mixed linear models is considered. It is assumed that covariance m
atrices commute after using the usual invariance procedure with respec
t to the group of translations. The test for vanishing of single varia
nce component is based on the locally best quadratic unbiased estimato
r of this component and rejects hypothesis if the ratio of positive an
d negative part of this estimator is sufficiently large. The power of
this test with powers of other four tests for two-way classification m
odels corresponding to block design is compared.