fit_multinomial_regression: Fits multinomial regression through 'optimx'

In group-wine/sommelieR: Fitting Linear, Multinomial, and Partial Proportional Odds Models to Predict Wine Quality

Description

Given a dataframe and a formula object, 'fit_multinomial_regression' will run a user-specified algorithm to fit multinomial linear regression for a user specified reference level.

Usage

fit_multinomial_regression(data, formula, ref_level, intercept = T,
  method = "BFGS", trace = 0, tol = 1e-04, itters = 200)

Arguments

data	a dataframe on which one would like to apply multinomial regression
formula	a formula obect - in the style of 'lm' which fits mulitnomial regression
ref_level	a character, the reference level of the multinomial model
intercept	default is TRUE, whether or not to include an intercept in the model
method	default is BFGS, argument is passed to optimx
trace	default is 0, passed to optimx
tol	default is 10e-5, passed to optimx
itters	default is 200, passed to optimx

Details

I should probably add the details of the assumptions of the model here.

Value

a list containing:

• the fitted estimates of the beta coefficients in multinomial regression

• The formula used to fit the model. Used to facilitate prediction.

group-wine/sommelieR documentation built on May 21, 2019, 1:43 p.m.