kernsm

Object of class <code>"array"</code> containing the original (response) data
  on a grid

Determines the kernel function. 
Object of class <code>"character"</code> kernel, can be any of
     <code>c("Gaussian","Uniform","Triangle","Epanechnicov","Biweight","Triweight")</code>.
Defaults to <code>kern="Gaussian"</code>

kern

Object of class <code>"integer"</code> vector of length <code>length(dy)</code> 
       determining the order of derivatives specified for the coordinate directios.

number of sectors to use. Positive weights are restricted to the sector
     selected by <code>sector</code>

nsector

Object of class <code>"integer"</code> between <code>1</code> and <code>nsector</code>. sector used.

sector

Object of class <code>"logical"</code> determines if sectors are symmetric with respect to the origin.   ~~Describe <code>symmetric</code> here~~

symmetric

Performs Kernel smoothing on a 1D, 2D or 3D grid by fft

smooth

nonparametric

The package contains R-functions implementing the
        Propagation-Separation Approach to adaptive smoothing as
        described in J. Polzehl and V. Spokoiny (2006),
        Propagation-Separation Approach for Local Likelihood
        Estimation, Prob. Theory and Rel. Fields, 135(3):335--362.  and
        J. Polzehl and V. Spokoiny (2004) Spatially adaptive regression
        estimation: Propagation-separation approach, WIAS-Preprint 998.

kernsm: Kernel smoothing on a 1D, 2D or 3D grid

Description

Usage

Arguments

Value

Details

References

See Also