modeler: Generic regression modelling function

In MXM: Feature Selection (Including Multiple Solutions) and Bayesian Networks

Generic regression modelling function

Description

Generic regression modelling function.

Usage

modeler(target, dataset = NULL, test = "testIndFisher")

Arguments

target	The target (dependent) variable. It can be a numerical variable, factor, ordinal factor, percentages, or time to event.
dataset	The predictor variable(s). It can be a vector, a matrix with continuous only variables. If there are no predictor variables leave this NULL.
test	Unlike reg.fit this accepts the test. The test argument is exactly like in all feature selection methods. This function accepts the following: "testIndReg", "testIndPois", "testIndNB", "testIndLogistic", "testIndMMReg", "testIndRQ", "testIndBinom", "censIndCR", "censIndWR", "censIndLLR", "testIndBeta", "testIndGamma, "testIndNormLog", "testIndTobit", "testIndQPois", "testIndQBinom", "testIndFisher", "testIndMultinom" and "testIndOrdinal".

Details

This is a generic regression function designed for continuous predictor variables only. It was useful for me so I decided to epxort it.

Value

A list including:

mod	The fitted model.
dev	The deviance. For some models though ("testIndMMReg", "testIndRQ", "censIndCR", "censIndWR", "testIndTobit", "testIndBeta", "testIndNB", ""testIndQPois", "testIndQBinom") this contains twice the log-likelihood.
bic	The BIC of the model. This is NA for the "testIndQPois" and "testIndQBinom" because they are quasi likhelidood models and hence have no BIC.
res	The residuals of the fitted model.

Author(s)

Michail Tsagris

R implementation and documentation: Michail Tsagris [e-mail]

References

Almost the same as in CondIndTests.

See Also

reg.fit, fbedreg.bic, mmpc.model, ridge.reg

Examples

#simulate a dataset with continuous data
dataset <- matrix(runif(100 * 5, 1, 100), nrow = 100 ) 
#the target feature is the last column of the dataset as a vector
target <- dataset[, 1]
dataset <- dataset[, -1]
a <- modeler(target, dataset)

MXM documentation built on Aug. 25, 2022, 9:05 a.m.