 
 
 
 
 
   
Sanford Weisberg
School of Statistics, University of Minnesota, St. Paul,
MN 55108-6042.
Supported by National Science Foundation Grant DUE 0109756.
January 10, 2002
 on a collection
 on a collection  predictors collected in
 predictors collected in  . In 
dimension reduction regression, we seek to find a few linear
combinations
. In 
dimension reduction regression, we seek to find a few linear
combinations 
 , such that all the
information about the regression is contained in these
, such that all the
information about the regression is contained in these  linear
combinations.  If
 linear
combinations.  If  is very small, perhaps one or two, then the
regression problem can be summarized using simple graphics; for
example, for
 is very small, perhaps one or two, then the
regression problem can be summarized using simple graphics; for
example, for  , the plot of
, the plot of  versus
 versus  contains
all the regression information.  When
 contains
all the regression information.  When  , a 3D plot contains
all the information.
Several methods for estimating
, a 3D plot contains
all the information.
Several methods for estimating  and relevant functions of
 and relevant functions of
 have been suggested in the literature.  In
this paper, we describe an
 package for three important dimension reduction methods,
including sliced inverse regression or
sir, sliced average variance estimates, or save, and principal
Hessian directions, or phd.  The package is very general and
flexible, and can be easily extended to include other methods of
dimension reduction.  It includes tests and estimates of the
dimension
 have been suggested in the literature.  In
this paper, we describe an
 package for three important dimension reduction methods,
including sliced inverse regression or
sir, sliced average variance estimates, or save, and principal
Hessian directions, or phd.  The package is very general and
flexible, and can be easily extended to include other methods of
dimension reduction.  It includes tests and estimates of the
dimension  , estimates of the relevant information including
, estimates of the relevant information including
 , and some useful graphical summaries as
well.
, and some useful graphical summaries as
well.
 
 
 
 
