Ummmmm, could we restrain the debate to statistical issues, and not get
into politics and name-calling?

A debate about the merits of MLE vs. multiple impuation for various
kinds of missing data problems (or more generally) would interest me,
and probably others on this list, and would, I think, be an excellent
example of  the benefits of  lists like this .  

A discussion of politics would also interest me, but this is not the
place for it. 

Name calling is just silly, and is an indication that one lacks better
arguments.  We're all professionals here; most of us, I dare say, with
graduate degrees.  Let's act like it.

Peter

Phil Good wrote
<<<
We're sure you don't.  Rumsfeld and Bush have similar problems.  But
I'll give you a hint:  Focus on the fine characteristics--use estimating
procedures that have them.  (And MLE's do under extremely restrictive
and unrealistic assumptions normally satisfied only in the academically
large.)
>>>

Peter L. Flom, PhD
Assistant Director, Statistics and Data Analysis Core
Center for Drug Use and HIV Research
National Development and Research Institutes
71 W. 23rd St
www.peterflom.com
New York, NY 10010
(212) 845-4485 (voice)
(917) 438-0894 (fax)


.
.
=================================================================
Instructions for joining and leaving this list, remarks about the
problem of INAPPROPRIATE MESSAGES, and archives are available at:
.                  http://jse.stat.ncsu.edu/                    .
=================================================================

Reply via email to