gaglm: Automatic selection of explanatory variable of multiple...

In ToshihiroIguchi/gaglm: Automatic selection of explanatory variable of multiple regression analysis by genetic algorithm

Description

It is generally difficult to select explanatory variables in multiple regression analysis. This package automatically selects explanatory variables of multiple regression analysis with genetic algorithm and it will be useful for creating your statistical model.

If the coefficient can not be calculated during optimization with the genetic algorithm, if the cook distance exceeds the threshold, if an error occurs, return the value of the model with only the intercept.

Usage

gaglm(formula, family = "gaussian", data, offset =NULL, method = "AIC", cook = 0.5, nfolds = 5,
popSize = 100, iters = 100, mutationChance = NULL, zeroToOneRatio=10)

Arguments

formula	an object of class "formula" (or one that can be coerced to that class): a symbolic description of the model to be fitted.
family	a description of the error distribution and link function to be used in the model. For gaglm this can be a character string naming a family function, a family function or the result of a call to a family function.
data	an optional data frame, list or environment (or object coercible by as.data.frame to a data frame) containing the variables in the model.
offset	this can be used to specify an a priori known component to be included in the linear predictor during fitting. This should be NULL or a numeric vector of length equal to the number of cases. One or more offset terms can be included in the formula instead or as well, and if more than one is specified their sum is used.
method	method is optimization target. You can select AIC or BIC or CV.
cook	It is the upper limit of cook distance. If the model exceeds the upper limit value, it returns the value of the model with only the intercept.
nfolds	number of divisions of cross validation. Valid only when method = "CV".
popSize	the population size.
iters	the number of iterations.
mutationChance	the chance that a gene in the chromosome mutates. By default 1/(size+1). It affects the convergence rate and the probing of search space: a low chance results in quicker convergence, while a high chance increases the span of the search space.
zeroToOneRatio	the change for a zero for mutations and initialization. This option is used to control the number of set genes in the chromosome.

Examples

set.seed(108)
result <- gaglm(Petal.Length~., data = iris)
plot(result)
summary(result)

ToshihiroIguchi/gaglm documentation built on May 6, 2019, 9:51 a.m.