loocv: Leave-one-out cross-validation

In switchSelection: Endogenous Switching and Sample Selection Regression Models

Leave-one-out cross-validation

Description

This function calculates root mean squared error (RMSE) for leave-one-out cross-validation of linear regression estimated via least squares method.

Usage

loocv(fit)

Arguments

fit	object of class lm.

Details

Fast analytical formula is used.

Value

This function returns a numeric value representing root mean squared error (RMSE) of leave-one-out cross-validation (LOOCV).

Examples

set.seed(123)
# Generate data according to linear regression
n <- 100
eps <- rnorm(n)
x <- runif(n)
y <- x + eps
# Estimate the model
model <- lm(y ~ x)
# Perform cross-validation
loocv(model)

switchSelection documentation built on Sept. 26, 2024, 5:07 p.m.