[R] missing values imputation

[A.J. Rossini]

Rolf Turner <rolf at math.unb.ca> writes:

> The EM algorithm requires an ``E'' step and an ``M'' step.  Harding
> and Rossini appear to be seriously suggesting that an R function
> could be written which would
>
> 	(a) Perform the E step in arbitrary contexts, and
> 	(b) For that given expected value, work out a procedure
> 	    to effect its maximization.
>
> Or maybe they're not serious.

Serious for a range of reasonable specific problems and appropriate
specification of the function (Remember that sufficient statistics
aren't unique, and would have to be specified!).  Think of it as a
macro.  Exercise left to the reader, see below.

> If you can write an R function to effect the EM ``algorithm'' --- in
> general, not just in a special case --- you'll win the Chambers Prize
> in computing and a few other things as well.

I believe there is an eligibility issue with the award you mention
(perhaps you are thinking of the ACM award?), but I suspect the
results, as in most software "publications", would be severe headaches
and grief from having to listen to complaints, gripes, and groaning.

Seldom are prizes, credit, and gratitude given, else Brian would be
drowning in them.

best,
-tony

-- 
rossini at u.washington.edu            http://www.analytics.washington.edu/ 
Biomedical and Health Informatics   University of Washington
Biostatistics, SCHARP/HVTN          Fred Hutchinson Cancer Research Center
UW (Tu/Th/F): 206-616-7630 FAX=206-543-3461 | Voicemail is unreliable
FHCRC  (M/W): 206-667-7025 FAX=206-667-4812 | use Email

CONFIDENTIALITY NOTICE: This e-mail message and any attachme...{{dropped}}