forwardSelectionJohn: Forward variable selection

In hansoleorka/myR: Collection of r functions for hansoleorka

Description

Perform a forward variable selection procedure as described by John in a glm setting

Usage

forwardSelectionJohn(y, X, family = gaussian(), Crit = "p.value",
  pValueThreshold = NULL, pValueLikelihoodRatio = 0.05, trace = TRUE)

Arguments

y	dependent variable
X	a data.frame of x variables
family	a description of the error distribution and link function to be used in the model. This can be a character string naming a family function, a family function or the result of a call to a family function. (See family for details of family functions.)
Crit	Criterion to be used for variable selection "p.value" or "aic" implemented.
pValueThreshold	a p-value threshold for single term models
pValueLikelihoodRatio	a p-value threshold for the likelihood ratio test
trace	logical printing model selection

Value

returns an object of class inheriting from "glm". See glm

Author(s)

Hans Ole &Oslashrka [e-mail]

hansoleorka/myR documentation built on May 17, 2019, 2:29 p.m.