In article <[EMAIL PROTECTED]>,
Jerry Dallal <[EMAIL PROTECTED]> wrote:
>Herman Rubin wrote:
>> In article <[EMAIL PROTECTED]>,
>> Jerry Dallal <[EMAIL PROTECTED]> wrote:
>> >Back in the "old days", the standard text for an undergraduate math stat
>> >course was Hogg & Craig. I had some fondness for Lindgren. I haven't
>> >taught this course in nearly 20 years. Which texts occupy their position
>> >today?
>> It was? There were many, and none too good. Personally, I
>> never like Hogg and Craig too well, and considered Lindgren to
>> be far worse.
>Then which ones did you find least objectionable?
Mood and Graybill would be in that category. I think the old
paperback Wilks compares well.
My fondness for
>Lindgren is due, no doubt, to my having had it as the assigned text
>for my first course as a student. It was one of the few texts
>geared toward undergraduates that bothered to state that maximum
>likelihood estimates were asymptotically efficient (without detailed
>proof, but at least the result is there) which, for better or worse,
>helps explain part of the fascination with mle's.
How does one define efficient? It does matter.
I believe it is more important to point out that, for regular
problems, the likelihood function is asymptotically that of
a normal translation parameter. This gets far more, as well
as an understanding of computational methods.
>> The question is which undergraduates. Someone who is planning
>> on doing decent graduate work should take an undergraduate
>> "pure mathematics" program intended for mathematicians, and no
>> probability and statistics below the level of Hoel, Port, and
>> Stone, if at all possible. If anything, I consider the level
>> to be on the low side. Other statistics books would be Bickel
>> and Doksum, or Cassella and Berger.
>Not an issue for me. I was merely curious as to what the latest
>"standard" was. Sounds like Cassella and Berger is worth a
>look-see.
I see it as a major issue. For those going on in any
direction, there should be no need to repeat. The real
prerequisite for a good course is not so much having had
abstract mathematics, but being able to take it.
Basic abstract mathematics belongs in elementary and
high school, not after years of brainwashing in how to
calculate. This is also true in statistics; those who
start with methods courses have major problems in even
attempting to consider the foundational problems later.
--
This address is for information only. I do not claim that these views
are those of the Statistics Department or of Purdue University.
Herman Rubin, Dept. of Statistics, Purdue Univ., West Lafayette IN47907-1399
[EMAIL PROTECTED] Phone: (765)494-6054 FAX: (765)494-0558
=================================================================
Instructions for joining and leaving this list and remarks about
the problem of INAPPROPRIATE MESSAGES are available at
http://jse.stat.ncsu.edu/
=================================================================
