Postscript version of this assignment
STAT 804: 99-3
Assignment 1
- 1.
- Let
be a Gaussian white noise process. Define
Compute and plot the autocovariance function of X.
- 2.
- Suppose that Xt is strictly stationary.
- (a)
- If g is some
function from Rp+1 to R show that
is strictly stationary.
- (b)
- What property must g have to guarantee the
analogous result with strictly stationary replaced by
order
stationary? [Note: I expect a sufficient condition on g; you need not
try to prove the condition is necessary.]
- 3.
- Suppose that
are iid and have
mean 0 with finite variance.
Verify that
is stationary and
that it is wide sense white noise.
- 4.
- Suppose Xt is a stationary Gaussian series with mean and autocovariance RX(k),
.
Show that
is stationary and find its mean and autocovariance.
- 5.
- Suppose that
where
is an iid mean 0 sequence with variance
.
Compute the autocovariance
function and plot the results for
and
.
(NOTE: I mean
and NOT ai here.)
I have shown in class that the roots of a certain polynomial must
have modulus more than 1
for there to be a stationary solution X for this difference equation.
Translate the conditions on the roots
to get
conditions on the coefficients a1,a2 and plot in the a1,a2 plane
the region for which this process can be rewritten as a causal filter
applied to the noise process
.
- 6.
- Suppose that
is an iid mean 0 variance
sequence and that
are constants.
Define
- (a)
- Derive the autocovariance of the process X.
- (b)
- Show that
implies
This condition shows that the infinite sum defining X converges
``in the sense of mean square''. It is possible to prove that this means
that X can be defined properly. [Note: I don't expect much rigour in this calculation.
Mathematically, you can't just define Xt as this question supposes since the
sum is infinite. A rigourous treatment asks you to prove that the condition
implies that
the sequence
is a Cauchy
sequence in L2. Then you have to know that this implies the existence of a limit
in L2 (technically, the point is that L2 is a Banach space). Then you have to
prove that the calculation you made in the first part of the question is mathematically
justified.]
- 7.
- Given a stationary mean 0 series Xt with autocorrelation
,
and a fixed lag D find the
value of A which minimizes the mean squared error
E[(Xt+d-AXt)2]
and for the minimizing A evaluate the mean squared error in terms of
the autocorrelation and the variance of Xt.
- 8.
- The semivariogram of a stationary process X is
(Without the 1/2 it's called the variogram.)
Evaluate
in terms of the autocovariance of X.
DUE: Monday, 27 September.
Richard Lockhart
1999-10-05