quantile.density {BMS} R Documentation

## Extract Quantiles from 'density' Objects

### Description

Quantiles for objects of class "density", "pred.density" or "coef.density"

### Usage

## S3 method for class 'density'
quantile(x, probs = seq(0.25, 0.75, 0.25), names = TRUE, normalize = TRUE, ...)

## S3 method for class 'coef.density'
quantile(x, probs = seq(0.25, 0.75, 0.25), names = TRUE, ...)

## S3 method for class 'pred.density'
quantile(x, probs = seq(0.25, 0.75, 0.25), names = TRUE, ...)


### Arguments

 x a object of class pred.density, coef.density, density, or a list of densities. probs numeric vector of probabilities with values in [0,1] - elements very close to the boundaries return Inf or -Inf names logical; if TRUE, the result has a names attribute, resp. a rownames and colnames attributes. Set to FALSE for speedup with many probs. normalize logical; if TRUE then the values in x\$y are multiplied with a factor such that their integral is equal to one. ... further arguments passed to or from other methods.

### Details

The methods quantile.coef.density and quantile.pred.density both apply quantile.density to densities nested with object of class coef.density or pred.density.
The function quantile.density applies generically to the built-in class density (as least for versions where there is no such method in the pre-configured packages).
Note that quantile.density relies on trapezoidal integration in order to compute the cumulative densities necessary for the calculation of quantiles.

### Value

If x is of class density (or a list with exactly one element), a vector with quantiles.
If x is a list of densities with more than one element (e.g. as resulting from pred.density or coef.density), then the output is a matrix of quantiles, with each matrix row corresponding to the respective density.

### Author(s)

Stefan Zeugner

quantile.default for a comparable function, pred.density and density.bma for the BMA-specific objects.

### Examples


data(datafls)
mm = bms(datafls[1:70,], user.int=FALSE)

#predict last two observations with preceding 70 obs:
pmm = pred.density(mm, newdata=datafls[71:72,], plot=FALSE)
#'standard error' quantiles
quantile(pmm, c(.05, .95))

#Posterior density for Coefficient of "GDP60"
cmm = density(mm, reg="GDP60", plot=FALSE)
quantile(cmm, probs=c(.05, .95))

#application to generic density:
dd1 = density(rnorm(1000))
quantile(dd1)

## Not run:
#application to list of densities:
quantile.density( list(density(rnorm(1000)), density(rnorm(1000))) )

## End(Not run)



[Package BMS version 0.3.5 Index]