Up: Stat 5102
Stat 5102 (Geyer) Final Exam
First define
so
and the CLT says
Now we apply the delta method to the transformation
because the random variable we want the the asymptotic of is
.
This has derivative
Hence the delta method says
Now
and
Hence
or
Let's look at the simplest moment first
Thus
is a perfectly good method of moments estimator of .
The CLT gives its asymptotic distribution
where
An asymptotic test can be based on the asymptotically pivotal quantity
which is approximately standard normal for large n, where Snis the sample standard deviation (the ``plug-in'' theorem allows
any consistent estimator of the population standard deviation ,
but the convenient one here is Sn).
To do the test in
this particular problem we need the mean of the beta distribution
(from p. 176 in Lindgren)
So under H0 (s = t)
That's the value of
that we plug in to compute Z
The first row of Table I in the appendix of Lindgren gives
P = 0.0001 for the one-tailed P-value. Hence the two-tailed
P-value is
P = 0.0002. (R says
P = 0.000225, so the table is
right to one significant figure.)
Since P < 0.05, reject H0.
First we have to find the posterior. The relevant formulas are given
in Example 5.2.4 in the notes, equations (5.17a) and (5.17b).
The precision of the data distribution is
1 / 25 = 0.04 and the
prior precision is
1 / 10 = 0.10. Hence from (5.17a) the posterior
precision is
and from (5.17b) the posterior mean is
The posterior standard deviation is
The HPD region is
or
or
(27.4081, 31.9649)
The model called ``Model 1'' in the ANOVA table has regression
function
where
.
This is obtained by setting
in the larger model (called ``Model 2''
in the ANOVA table). Hence ``Model 1'' is a submodel of ``Model 2.''
The table gives a P-value
P = 0.004277 for the test of model comparison.
Since the P-value is very small, this is strong evidence against the
small model. Thus we conclude that the piecewise linear model fits
and the simple linear model (``Model 1'') doesn't.
This problem was a learning experience for the teacher.
We needed some homework problems like this. It was harder
than I thought it would be. Most people had no clear idea of how
to show the models were nested. Only two people got full credit.
In order two show the models are nested, you need to show one of
two things.
- Every distribution in the little model is also in the big model.
Here the models differ only in their regression functions, so you need
to show that every regression function in the little model is also in
the big model.
- For regression models, we also have the condition that the range
of the design matrix for the little model is a subspace of the range
of the design matrix for the big model.
These two conditions come to much the same thing (as we shall see below).
We can write the regression functions for the little model
but this is a bad idea given the form of the regression function for the
big model
|
(1) |
Because the two 's are not the same. Better to chose another
letter (or at least an embellished alpha) for the intercept in the little
model
|
(2) |
Now the question to be answered is what values of ,
and
in (1) give (2)? It is not enough to just assert
that there are some such values. You have to find them.
A little thought suggests
,
which collapses the
two cases in (1) to one
|
(3) |
but the result still doesn't exactly match (2).
You still have to remark about chosing
,
or what is the same,
.
The design matrices for the two models are
How does one show that the range
is a subspace of the range of
?
One needs to show that for any two-vector
,
there exists a three-vector
such that
But this is exactly the same question as asked and answered above,
because
is the regression function
described in matrix language. Exactly the same argument shows that
and
does the job.
The density of the data is
The prior density is
(the normalizing constant doesn't matter).
The likelihood for a sample of size n is
or, if we introduce the variables
,
The last term can be dropped, since it does not contain the parameter,
giving
The unnormalized posterior (likelihood times prior) is
This is clearly proportional to
a
.
So that is the posterior density.
Sanity Check: Does this make sense? Are both parameters of
the posterior positive? Clearly
is positive, because
we need
for the prior to make sense. How
about
? At first sight this doesn't look positive.
We need
for the prior to make sense, but how do we know that
the other bit doesn't make it negative? Have to think a bit.
0 < xi < 1,
so
(logs of numbers less than one are negative), so
is actually positive despite its appearance, and
everything is o. k.
The regression coefficient in question is
-0.011464 and R gives its standard error as 0.007784
and the degrees of freedom for error as 17.
We only need to look up the t critical value from Table IIIb in Lindgren,
which for 90% confidence is 1.74 (note not in the column headed 90,
but in the next one over that has 1.645 as the appropriate z critical
value at the bottom).
Thus the interval is
or
or
(-0.02500816, 0.0020801)
The sample median
is asymptotically normal center
m the population median and variance
1 / 4 n f(m)2 (Corollary 2.28
in the notes). Here the population median is zero by symmetry and
.
Hence
Up: Stat 5102
Charles Geyer
2000-05-13