Description
These functions were developed to support functional data
analysis as described in Ramsay, J. O. and Silverman, B. W.
(2005) Functional Data Analysis. New York: Springer. They were
ported from earlier versions in Matlab and S-PLUS. An
introduction appears in Ramsay, J. O., Hooker, Giles, and
Graves, Spencer (2009) Functional Data Analysis with R and
Matlab (Springer). The package includes data sets and script
files working many examples including all but one of the 76
figures in this latter book. The principal changes to version
2.2.6 are: 1. Major enhancements to function smooth.basis as
well as the functions that call it. New or revised arguments
are: "wtvec" may now be a positive symmetric matrix as well as
a vector "covariates" for inputting covariate matrices that
explain some fraction of the data to be smoothed (often called
"semiparametric smoothing") "method=qr" enables an algorithm
based on the qr- decomposition that will be more accurate than
the usual approach relying on the Choleski decomposition. It
will, however, be slower. 2. Greatly expanded examples in the
smooth.basis.Rd file that show a wider range of uses of this
function. 3. Function data2fd has been replaced by function
Data2fd for simple smoothing problems. Data2fd is designed to
be invoked with various argument configurations. 4. And the
usual fixes of reported bugs, especially in the registraton
functions, landmarkreg and register.fd.