ConstrainedGlm.fit: Constrained logistic regression In this function we create a...

In frbl/OnlineSuperLearner: Online SuperLearner package

Description

Constrained logistic regression In this function we create a regression for which the predicted probabilities are contstrained. That is, they can not be less than a minimum of delta, or a maxiumum of 1 - delta.

Usage

ConstrainedGlm.fit(formula, delta, data, fall_back_to_glm = TRUE,
  previous_glm = NULL, ...)

Arguments

formula	the formula to use for the regression
delta	the threshold used for constraining the probabilities
data	the data to train the glm on
fall_back_to_glm	boolean should we fall back to traditional glm
previous_glm	glm object. A previously trained GLM instance, so it can be updated
...	the other arguments passed to GLM

Value

a fitted glm

frbl/OnlineSuperLearner documentation built on Feb. 9, 2020, 9:28 p.m.