input_checker: Helper function for input checking

In postDoubleR: Post Double Selection with Double Machine Learning

Description

This functions checks the input to the double_select function for compliance with the default methods used, confirming that the inputs are viable. It is a helper - no interaction with the user should happen unless the user explicitly calls this function.

Usage

input_checker(X_matrix, Y_vector, W_vector, specify.custom,
  test.inputs = TRUE)

Arguments

X_matrix	A matrix of covariates (must be all numeric)
Y_vector	A vector of the target variable, of same length as the number of rows of X, must be numeric
W_vector	A vector of the treatment variable, of same length as the number of rows of X, must be numeric
specify.custom	disables input checking by default, and leaves it to the user.
test.inputs	If set to FALSE disables input checking, the default is TRUE.

Details

The function will throw a warning if it is disabled ( the input is not checked) or stop the processing if the input is checked, but incorrect. Disables checking for custom functions by default.

Value

A message indicating the status of input checking, or lack thereof.

Examples

  n = 2000; p = 10
  X = matrix(rnorm(n*p), n, p)
  W = rbinom(n, 1, 0.4 + 0.2 * (X[,1] > 0))
  Y = pmax(X[,1], 0) * W + X[,2] + pmin(X[,3], 0) + rnorm(n)

input_checker(X_matrix = X, Y_vector = Y, W_vector = W,
specify.custom = NULL, test.inputs = TRUE)

postDoubleR documentation built on Oct. 7, 2019, 5:05 p.m.