Alas, the desirable properties of an estimate arise for an MLE only if that distribution is normal.
"Robert J. MacG. Dawson" <[EMAIL PROTECTED]> wrote:
"Robert J. MacG. Dawson" <[EMAIL PROTECTED]> wrote:
Peter Flom wrote:
>
> Ummmmm, could we restrain the debate to statistical issues, and not get
> into politics and name-calling?
An excellent plan.
My own understanding is that *if* we know for sure that the population
distribution is from a certain parametric family, there are good
arguments for ML.
The problems arise if we think (or assume) we know this and it's not
so.
-Robert Dawson
.
.
=================================================================
Instructions for joining and leaving this list, remarks about the
problem of INAPPROPRIATE MESSAGES, and archives are available at:
. http://jse.stat.ncsu.edu/ .
=================================================================
Phillip Good
http.ms//www.statistician.usa
"Never trust anything that can thi! nk for itself if you can't see where it keeps its brain." JKR
http.ms//www.statistician.usa
"Never trust anything that can thi! nk for itself if you can't see where it keeps its brain." JKR
Do you Yahoo!?
Yahoo! Mail - More reliable, more storage, less spam
