Packages aov, modreg, lqs, psplines

Prof Brian Ripley Prof Brian Ripley <>
Mon, 31 Aug 1998 15:19:26 +0100 (BST)

I now have versions of code that is destined (I believe) for 0.63 which
is in a suitable state for comment. The files are at  

(Our www server is being moved, so may be intermittently down, but this
ftp server should be stable.)  All are R packages, for the moment for
personal use only (no re-distribution). Use with 0.62.3 or 0.63 (although
I am aware of some problems with use with 0.63 that I have reported).


aov with Error terms, proj, model.tables, se.contrast, replications, 
eff.aovlist, C, dummy.coef, add1, drop1, step, kappa, labels.

This is in I believe close to final form.


ksmooth                  Kernel Regression Smoother
loess                    Local Polynomial Regression Fitting
loess.control            Set Parameters for Loess
plot.ppr                 Plot Ridge Functions for Projection Pursuit
                            Regression Fit
ppr                      Projection Pursuit Regression
predict.loess            Predict Loess Curve or Surface
predict.smooth.spline    Predict from Smoothing Spline Fit
scatter.smooth           Scatter Plot with Smooth Curve Fitted by Loess
smooth.spline            Fit a Smoothing Spline
supsmu                   Friedmans's SuperSmoother

Probably only bug-fixing left, but I would welcome comments about the
extent of the loess functionality.


cov.rob                  Robust Estimation of Multivariate Location and
lqs                      Resistant Regression by Least Trimmed and Least
                            Quantile Sum of Squares
lmsreg, ltsreg, cov.mve  Compatibility functions

This is much less complete (and the claimed mcd method is not yet
operational).  Comments please both on the design and from any experts
out there on the methodology used. (BTW, as all the programs I have give
different answers, it is very hard to establish the true answer. I am
fairly convinced that both S-PLUS versions are slightly wrong.)

I plan to add S-estimation, a general M-estimator (based on my function
rlm) and MM-estimation to this over the next few weeks.

While I am posting, a R port of Jim Ramsay's psplines package is also there
en route to CRAN, file (pspline_1.0-1.tar.gz) as well as an update of the
V&R `R' Complements to 0.62.3.

Brian D. Ripley,        
Professor of Applied Statistics,
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-devel mailing list -- Read
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: