Final exam is take-home, just like the other exams. It is due Tuesday December 19 by 4:30 when the Statistics Department office (Ford 313) closes.
The test is this web page.
The instructor (Geyer) will answer e-mail about the exam and put any answers of general interest here and on the exam page. I will also be in my office a lot during the exam. Just drop in with questions or phone before you come if you want to be sure I will be there.
It was noted that some old exam solutions were not readable. Now they all are
All are password protected, the usual user name and password works.
As announced, take home, due Wednesday, November 22, 2006. The due date has been extended to Wednesday, because they would probably not be graded until the following Monday anyway.
The test is this web page. To stand out from spam, put 5601 in the subject line. Students can also ask Prof. Chatterjee for clarifications.
Anyone wanting to hand in their exam early should hand it to Prof. Chatterjee or to one of the office staff (in Ford 313). Do not put it in anyone's mailbox or under anyone's door.
Query 1 about Question 2
Someone asked about why
ltsreg doesn't give the same
answers when run multiple times, even on the given data (never mind
on random bootstrap data). Yes, that's what it does.
help is clear as mud, but, as mentioned in class, exact minimization
of the objective function is very hard so generally random search algorithms
If you want
exact answer, you can add the argument
nsamp = "exact"
ltsreg function, but then it will take forever —
I have no idea how long, I tried it, took a long shower, it was still running,
so I killed it. Please don't experiment with this
rweb.stat.umn.edu. If you're running R at home you can try
what you like.
If you want
a better but non-exact answer, you can add the
nsamp = 1e3 or some other number,
the higher the number the better the answer (I think).
However, anyone who ignores all this and just uses the default
won't be marked off for that. Don't mess with this unless you are
(1) curious and (2) have the time.
(Added a bit later) if I use
nsamp = 1e3 the bootstrap
nboot <- 250 takes 15 seconds
If I use
nsamp = 5e3
nboot <- 250, it takes 58 seconds
That's more than enough time for one job during a test.
Anyone who wants to experiment with higher
do it on your own computer, or, at least, after the test.
New! The last homework (number 7) has been graded and is in a box on the floor outside the instructor's office (Ford 356) if you want to pick it up.
Homework 7 solutions posted.
Two new handouts on theory page. One on subsampling bootstrap, one on smoothing.
New! Homework 5 solutions posted (in the usual place with the usual user name and password).
What is LTS regression?
help for the R
ltsreg function says that
LQS regression minimizes a specified quantile of the squared residuals,
LMS regression minimizes the median (0.5 quantile) of the squared residuals,
and LTS regression minimizes the sum of the
quantile smallest squared
residuals, the default being
floor(n/2) + floor((p+1)/2), which
is roughly 1 / 2 when
n (number of cases) is much larger
p (number of regression coefficients). Thus LTS regression
minimizes the sum of the squares of the smallest half of the residuals.
help for the R
ltsreg function says that LTS regression is more
efficient than LQS (and its special case LMS), having different rates of
n1 ⁄ 2 for LTS but
n1 ⁄ 3 for LQS and LMS.
Homework 5, Problem 1 had additional wording
added to make it clear that
this estimate refers
New! Homework 5 now posted.
Tentative schedule to second midterm.
|Fri Nov 03
|Mon Nov 13
|Fri–Mon Nov 17–20
|Th–Fri Nov 23–24
Info about installing and using R for those who wish to have R on their own computers.