min_span: min_span

In JakubStats/marge: Multivariate Adaptive Regression splines using Generalized estimating Equations

min_span

Description

A truncation function applied on the predictor variable for knot selection.

Usage

min_span(X_red, q, minspan = NULL, alpha = 0.05)

Arguments

X_red	: a vector of reduced predictor variable values.
q	: the number of predictor variables used.
minspan	: the set minimum span value. The default is minspan = NULL.
alpha	: see Friedman (1991) equation (43). The default is 0.05.

Details

This function selects a minimum span between the knots to mitigate runs of correlated noise in the input data and hence avoiding estimation issues, this equation comes from Friedman (1991) equation 43.

Value

min_span returns a vector of truncated predictor variable values.

Author(s)

Jakub Stoklosa and David I. Warton.

References

Friedman, J. (1991). Multivariate adaptive regression splines. The Annals of Statistics, 19, 1–67.

Stoklosa, J. and Warton, D.I. (2018). A generalized estimating equation approach to multivariate adaptive regression splines. Journal of Computational and Graphical Statistics, 27, 245–253.

JakubStats/marge documentation built on Feb. 25, 2024, 9:38 p.m.