opt.ic: Optimization routine based on information criteria.

In BPJandree/AutoGLM: Automated fitting, model selection, and documentation functions for GLM modelling of binary response variables.

Description

This function optimizes a model using information critera as a decision rule. This solves many of the problems related to model selection based on hypothesis tests, see also opt.h. In finite samples, the AIC is known to favor large models. The corrected AIC is a slightly stricter measure.

Usage

opt.ic(model, Y, X, KLIC = "AICc", returntype = "model", tracelevel = 0,
  memorymanagement = FALSE)

Arguments

model	The model to be optimized. Supports "lm" for the linear probability model, "logit" for the logistic probability model, and "probit" for the probit model.
Y	The binary response variable.
X	A dataframe with collumns of exogenous regressors.
KLIC	information criterion to be used, "AIC" or "AICc", See also IC
returntype	"model", "data", or "colnames"
tracelevel	level of printing.
memorymanagement	logical, indicating whether memory should be more actively managed.

Value

"model", "data", or "colnames", to be specified in returnype.

Examples

randomlogit <- simulateLogit(nobs=500, pars = c(0.5, -0.4, -0.3, 0.1, 0.05, 0.025, 0, 0, 0, 0))
Y=randomlogit[,1]
X=randomlogit[,-1]
opt.ic(model="lm", Y, X)

BPJandree/AutoGLM documentation built on May 5, 2019, 10:25 a.m.