R-ers:
I was wondering if anyone had suggestions on how to implement a GAM
in a quantile fashion? I'm trying to derive a model of a "hull"
of
points which are likely to require higher-order polynomial fitting (e.g.
splines)-- would quantreg be sufficient, if the response and predictors
are all continuous? Thanks!
--j
On Fri, 2009-05-29 at 16:51 -0700, Jonathan Greenberg wrote:> R-ers: > > I was wondering if anyone had suggestions on how to implement a GAM > in a quantile fashion? I'm trying to derive a model of a "hull" of > points which are likely to require higher-order polynomial fitting (e.g. > splines)-- would quantreg be sufficient, if the response and predictors > are all continuous? Thanks!If you're just after the AM bit of GAM, then yes, I think quantreg contains functions to do as you wish. See ?rqss and ?qss for models that allow smoothing splines in quantile regression. Alternatively, I think package VGAM may also contain something of use. HTH G> > --j > > ______________________________________________ > R-help at r-project.org mailing list > https://stat.ethz.ch/mailman/listinfo/r-help > PLEASE do read the posting guide http://www.R-project.org/posting-guide.html > and provide commented, minimal, self-contained, reproducible code.-- %~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~% Dr. Gavin Simpson [t] +44 (0)20 7679 0522 ECRC, UCL Geography, [f] +44 (0)20 7679 0565 Pearson Building, [e] gavin.simpsonATNOSPAMucl.ac.uk Gower Street, London [w] http://www.ucl.ac.uk/~ucfagls/ UK. WC1E 6BT. [w] http://www.freshwaters.org.uk %~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%
Hi Jonathan,>> I was wondering if anyone had suggestions on how to implement a GAM >> in a quantile fashion?Take a look at the gamlss package. Regards, Mark. Jonathan Greenberg-2 wrote:> > R-ers: > > I was wondering if anyone had suggestions on how to implement a GAM > in a quantile fashion? I'm trying to derive a model of a "hull" of > points which are likely to require higher-order polynomial fitting (e.g. > splines)-- would quantreg be sufficient, if the response and predictors > are all continuous? Thanks! > > --j > > ______________________________________________ > R-help at r-project.org mailing list > https://stat.ethz.ch/mailman/listinfo/r-help > PLEASE do read the posting guide > http://www.R-project.org/posting-guide.html > and provide commented, minimal, self-contained, reproducible code. > >-- View this message in context: http://www.nabble.com/Quantile-GAM--tp23788632p23792799.html Sent from the R help mailing list archive at Nabble.com.
There are possibilities with rqss() as someone else mentioned. But you
can also conduct a lot of useful modeling just by using b-splines within
the the rq function - something like
my.result <- rq(y ~ bs(x,degree=3)), where bs() is the b-spline function
from the splines package. You get to specifiy the degree of polynomial
and number and location of knots.
Brian
Brian S. Cade, PhD
U. S. Geological Survey
Fort Collins Science Center
2150 Centre Ave., Bldg. C
Fort Collins, CO 80526-8818
email: brian_cade@usgs.gov
tel: 970 226-9326
From:
Jonathan Greenberg <greenberg@ucdavis.edu>
To:
"r-help@r-project.org" <r-help@r-project.org>
Date:
05/29/2009 05:55 PM
Subject:
[R] Quantile GAM?
Sent by:
r-help-bounces@r-project.org
R-ers:
I was wondering if anyone had suggestions on how to implement a GAM
in a quantile fashion? I'm trying to derive a model of a "hull"
of
points which are likely to require higher-order polynomial fitting (e.g.
splines)-- would quantreg be sufficient, if the response and predictors
are all continuous? Thanks!
--j
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide
http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
[[alternative HTML version deleted]]