approximation {EQL} R Documentation

## An Approximation Class

### Description

An object of class approximation stores the approximation nodes together with the approximation itself. Some meta information is saved as well.

### Usage

approximation(y, approx, n,
type = c("standardized", "mean", "sum"),

## S3 method for class 'approximation'
plot(x, do.annotate = TRUE, ...)


### Arguments

 y a numeric vector or array giving the approximation nodes. approx a numeric vector or array giving the approximated values at y. n a positive integer giving the number of i.i.d. random variables in the sum. type a character string giving the type of approximation, i.e. which kind of sum is to be approximated. Must be one of (“standardized”, “mean”, “sum”), representing the shifted and scaled sum, the weighted sum and the raw sum. Can be abbreviated. approx.type a character string giving the approximation routine used. Must be one of of (“Edgeworth”, “Saddlepoint”) and can be abbreviated. x an approximation object. do.annotate logical. If TRUE (the default) the value of the argument n is added to the plot. ... other parameters to be passed through to the plotting function. Giving a named argument for any of main sub type xlab ylab overrides the default values in plot.approximation.

### Value

An object of class approximation contains the following components:

 y a numeric vector of values at which the approximation is evaluated (the approximation nodes). approx a numeric vector containing the approximated values at the approximation nodes y. type a character string giving the type of sum considered, i.e. one of (“standardized”, “mean”, “sum”). n a positive integer giving the number of i.i.d. random variables in the sum. approx.type a character string giving the type of approximation.

### Author(s)

Thorn Thaler

edgeworth, saddlepoint