gradient_descent_OLS_cv: A function fitting the OLS model

In cz354/bis557: The package for bis557's homework

Description

This is a function fitting the OLS model using gradient descent that calculates the penalty based on the out-of-sample accuracy. Here we use cross validation to calculate the out-of-sample accracy.

Usage

gradient_descent_OLS_cv(
  formula,
  data_frame,
  nfolds = 10,
  contrasts = NULL,
  lambda = 1e-04,
  tolerence = 1e-20,
  beta1 = 1,
  max_itr = 1e+06
)

Arguments

formula	a formula of linear model
data_frame	a data_frame
nfolds	Default is 10. the number of folds for cross validation
contrasts	Default is NULL. a list of constasts for factor variables
lambda	Default is 0.0001. The speed of gradient descent
tolerence	Default is 1e-20. The minimum difference between the old ssr and the update ssr.
beta1	Default is 1. The initial value of beta.
max_itr	Default is 1e6. The maximum number of iterations

Examples

data(iris)
gradient_descent_OLS_cv(Sepal.Length ~ ., iris,nfolds=10)

cz354/bis557 documentation built on Dec. 20, 2020, 3:05 a.m.