[R] estimating missing data

[Adaikalavan Ramasamy]

The knn algorithm imputes the missing value by finding k-closest/similiar
(Euclidean or correlation) rows. Should be useful for genetic data whereby
genes (rows) that are co-regulated have the similiar expression profiles.
?knn gives you reference to paper that compare this method with SVDimpute
and row averages.

There is a library called 'missing' in S-PLUS which does EM besides many
other fairly involved multiple imputation algorithms. It comes supplied with
a 170 page help manual. But I know of no similiar versions in R. Sorry if
this isn't very helpful.

Adai.

----- Original Message -----
From: <Xavier.Abulker at fimat.com>
To: <r-help at stat.math.ethz.ch>
Sent: Friday, July 26, 2002 4:50 PM
Subject: [R] estimating missing data


> Hello R group
>
> Do you know if an EM algorithm exits for R to estimate missing data in a
> sample?
> I just found knn algorithm in to the package emv but it doesn't look to be
> the usual EM algorithm.
> Thanks
> Xavier
>
> -.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.
-.-.-
> r-help mailing list -- Read
http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
> Send "info", "help", or "[un]subscribe"
> (in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch
>
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._.
_._
>

-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._