summary.cv4abc: Calculates the cross-validation prediction error

In abc: Tools for Approximate Bayesian Computation (ABC)

Calculates the cross-validation prediction error

Description

This function calculates the prediction error from an object of class "cv4abc" for each parameter and tolerance level.

Usage

## S3 method for class 'cv4abc'
summary(object, print = TRUE, digits = max(3,
getOption("digits")-3), ...)

Arguments

object	an object of class "abc".
print	logical, if TRUE prints messages. Mainly for internal use.
digits	the digits to be rounded to. Can be a vector of the same length as the number of parameters, when each parameter is rounded to its corresponding digits.
...	other arguments passed to density.

Details

The prediction error is calculated as \frac{∑((θ^{*}-θ)^2)}{nval\times Var(θ)}, where θ is the true parameter value, θ^{*} is the predicted parameter value, and nval is the number of points where true and predicted values are compared.

Value

The returned value is an object of class "table", where the columns correspond to the parameters and the rows to the different tolerance levels.

See Also

cv4abc, plot.cv4abc

Examples

## see ?cv4abc for examples

abc documentation built on May 20, 2022, 1:11 a.m.