On Sat, 2 Mar 2002 markhall at gol.com wrote:
> Is there a way of getting a list of indices or something indicating which
set
> of points lqs when doing a regression? The $bestone, seems to return only
> 2 pts. no matter how good or bad the fit. I checked the archive for the
past
> few months, but didn't find anything.
That is what bestone does return. It's on my agenda to document the lqs
return values, but I started with the commoner ones like lm! In any case,
you have the code to read.
For example
data(stackloss)
set.seed(123)
(fit <- lqs(stack.loss ~ ., data = stackloss))
> fit$bestone
[1] 7 10 11 15
That is the list of points used for the best fit found. It always tries
subsets of size p.
lm (stack.loss ~ ., data = stackloss, subset = fit$bestone)
is slightly different: see the lqs help page for why.
--
Brian D. Ripley, ripley at stats.ox.ac.uk
Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/
University of Oxford, Tel: +44 1865 272861 (self)
1 South Parks Road, +44 1865 272860 (secr)
Oxford OX1 3TG, UK Fax: +44 1865 272595
-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
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
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._