Reading: Chapter 6.1-6.
Assume:
Define: H= X(XT X)-1 XT, the hat matrix so that M=I-H.
If also
If also
are independent then
Notice and that H is .
Some algebraic simplification of the variances above is possible.
But
ASIDE: as you read that sequence of formulas you will see that I expect you to remember a number of algebraic facts about matrices:
So
Thus
Definition: A matrix Q is idempotent if
Estimation of
is based on the error sum of squares defined by
Now note that
But
for
and
so
Definition: The trace of a square matrix Q is defined by
Marvelous Matrix Identity (cyclic invariance of the trace).
Suppose that
and
so that
and
are both square. Then
The same idea works with more than two matrices provided the product is
square so, e.g.,
Another algebraic identity for the trace:
SO:
Notice that p is the number of columns of X including the column of 1's if present.
So the Mean Squared Error, ESS/(n-p) is an unbiased estimate of .
Here is an example of some of the matrix algebra I was doing in class.
Consider the weighing design where two objects of weights
and
are weighed individually and together. The resulting design
matrix is
So
The hat matrix is
You can also check that H is idempotent.