CV_logisticc: CV Logisticc (c++)

In MGallow/logitr: Penalized Logistic Regression

Description

Computes the coefficient estimates for logistic regression. ridge regularization and bridge regularization optional. This function is to be used with the "logisticc" function.

Usage

CV_logisticc(X, y, lam = 0L, alpha = 0L, penalty = "none",
  intercept = TRUE, method = "IRLS", tol = 1e-05, maxit = 10000,
  vec = 0L, init = 0L, criteria = "logloss", K = 5L)

Arguments

X	matrix
y	matrix or vector of response values 0,1
lam	vector of tuning parameters for ridge regularization term. Defaults to 'lam = 0'
alpha	vector of tuning parameters for bridge regularization term. Defaults to 'alpha = 1.5'
penalty	choose from c('none', 'ridge', 'bridge'). Defaults to 'none'
intercept	Defaults to TRUE
method	optimization algorithm. Choose from 'IRLS' or 'MM'. Defaults to 'IRLS'
tol	tolerance - used to determine algorithm convergence. Defaults to 1e-5
maxit	maximum iterations. Defaults to 1e5
vec	optional vector to specify which coefficients will be penalized
init	optional initialization for MM algorithm
criteria	specify the criteria for cross validation. Choose from c("mse", "logloss", "misclass"). Defauls to "logloss"
K	specify number of folds in cross validation, if necessary

Value

returns best lambda, best alpha, and cross validation errors

MGallow/logitr documentation built on May 6, 2019, 12:06 a.m.