New! Grades have been submitted. They should be available in the U computer system.
New! Students can pick up exams in the School of Statistics office (313 Ford Hall). They are open 8:00-4:30 Monday through Friday.
New! Grade distributions for final exam posted.
New! Solutions for final exam posted (usual user name and password, like homework solutions).
Several biostatistics students have asked me about the likelihood ratio
test and whether we will go back and cover that. The problem is that
what the DeGroot and Schervish have is not what you need to know. I'm
not sure we have time to cover that, and in any case the relevant theory
beyond the scope of this course. As a possible helpful alternative,
I am making available some
notes from the PhD level theory course,
the theory of the likelihood ratio test and related test being Chapter 4.
Theorems 4.1, 4.2, and 4.3 describe three asymptotically equivalent
tests (Wilks, Rao, and Wald) for comparing models using maximum likelihood.
Where those theorems say ELE (efficient likelihood estimator) read MLE
(maximum likelihood estimator). Don't bother reading the proofs, just
understand what the theorems and the surrounding explanations say.
I will of course answer questions about this.
|Exam||Date and Time|
|First Midterm||Wednesday, February 21|
|Second Midterm||Wednesday, April 4|
|Final Exam||1:30pm-3:30pm Thursday, May 10|
The final exam date and time is set by the U.