createTPRSmodelmatrix: Create matrix of Thin-Plate Regression Splines (TPRS)

In predkmeans: Covariate Adaptive Clustering

Description

Wrapper function for creating a matrix of thin-plate regression splines (TPRS) to be used in a regression analysis.

Usage

createTPRSmodelmatrix(
  data,
  df = 5,
  covarnames = NULL,
  xname = "x",
  yname = "y",
  TPRSfx = TRUE,
  matrixonly = TRUE
)

Arguments

data	Matrix or data frame of data
df	Degrees of freedom for thinplate splines. This does not include an intercept, so the k argument of s() is k = df + 1.
covarnames	Names of other covariates to be included in the model matrix.
xname	Name of variable the provides the x-coordinate of location.
yname	Name of variable the provides the y-coordinate of location.
TPRSfx	Should the TPRS degrees of freedom be fixed. Passed as the fx argument to s().
matrixonly	Logical indicator of whether only the model matrix should be returned, or the full output from gam.

Author(s)

Joshua Keller

See Also

createPCAmodelmatrix, predkmeansCVest

Examples

n <- 200
x <- runif(n=n, 0, 100)
y <- runif(n=n, 0, 100)
d <- data.frame(x=x, y=y)
mx <- createTPRSmodelmatrix(data=d, df=5)

predkmeans documentation built on Jan. 11, 2020, 9:29 a.m.