Predict.matrix.msg.smooth: Multidimensional Scaling for Generalized additive models -...

In dill/msg: Multidimensional Scaling for Generalized Additive Models

Description

Provides smoothing methods for multidimensional scaling-based projections of the data.

Usage

## S3 method for class 'msg.smooth'
Predict.matrix(object, data)

Arguments

object	a smooth specification object, usually generated by a term s(...,bs="ds",...). Note that xt object is needed, see Details.
data	a list containing just the data (including any by variable) required by this term, with names corresponding to object$term (and object$by). The by variable is the last element.

Details

Usage is split into two cases: (1) For geographical smooths of two coordinates, within-area distances with respect to the boundary are used to create a distance matrix that is then projected into as many dimensions as required. (2) General distance smoothing where distances are calculated between observations based on all covariates supplied using Euclidean or Mahalanobis distances.

In both cases smoothing is performed using Duchon splines (see Duchon.spline for more information).

dill/msg documentation built on May 15, 2019, 8:30 a.m.