backward_sel_WIC: backward_sel_WIC

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

backward_sel_WIC

Description

Backward selection function for MARGE - uses the Wald information criterion (WIC).

Usage

backward_sel_WIC(
  Y,
  N,
  n,
  B_new,
  id,
  family = "gaussian",
  corstr = "independence",
  nb = FALSE,
  is.gee = FALSE,
  ...
)

Arguments

Y	: the response variable.
N	: the number of clusters.
n	: the maximum cluster size.
B_new	: the model matrix.
id	: the ID for each individual in the cluster.
family	: the specified "exponential" family for the GLM. The default is family = "gaussian".
corstr	:the specified "working correlation" structure. The default is corstr = "independence".
nb	: a logical argument, is the model a negative binomial model? The default is FALSE.
is.gee	: is this a GEE model? The default is FALSE.
...	: further arguments passed to or from other methods.

Value

backward_sel_WIC returns the Wald statistic from the fitted model (the penalty is applied later on).

Author(s)

Jakub Stoklosa and David I. Warton

References

Stoklosa, J. Gibb, H. Warton, D.I. Fast forward selection for Generalized Estimating Equations With a Large Number of Predictor Variables. Biometrics, 70, 110–120.

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.

See Also

backward_sel

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