[R-pkgs] ppls: version 1.02 including a new data set

Nicole Kraemer nkraemer at cs.tu-berlin.de
Thu Jul 10 17:28:19 CEST 2008


Dear R users,

an update of the package ppls - Penalized Partial Least Squares - is now 
available on CRAN.

It implements the methods described in

N. Krämer, A.-L. Boulesteix, G. Tutz
"Penalized Partial Least Squares with Applications to B-Spline 
Transformations and Functional Data"
Chem. Intell. Lab. Sys. 2008
http://dx.doi.org/10.1016/j.chemolab.2008.06.009


Features of the package include

* the estimation of functional data with penalized PLS,
* the estimation of generalized additive models with penalized PLS based 
on spline transformations,
* model selection for both methods based on cross validation.

The most important changes since 1.01 are

(1) a more efficient implementation of the penalized PLS algorithm that 
decreases the run-time substantially,
(2) the inclusion of the data set "cookie" that contains measurements 
from quantitative near-infrared spectroscopy.

Best regards,

Nicole & Anne-Laure


-- 
Dr. Nicole Krämer
TU Berlin
Machine Learning/Intelligent Data Analysis	fon: (+49) 30 314 78627
Franklinstr. 28/29, 10587 Berlin, Germany	fax: (+49) 30 314 78622

web: http://ml.cs.tu-berlin.de/~nkraemer




More information about the R-packages mailing list