STAT 350: 95-3
Assignment 6
If we fit a simple linear regression of the form
for which the design matrix is as above,
evaluate the non-centrality parameter of the t test of
when in fact
and
. What would the power of a
two sided 1% level t test of this null hypothesis be? How many
times would we have to replicate this design to get a power of 0.9 for
a 1% level test?
Assume that in fact and
.
where the errors have variances
and
the
are known quantities.
Find an explicit algebraic formula for the weighted least squares
estimate of
.