R: Univariate conditional predictive cumulative distribution...

NMixPredCondCDFMarg {mixAK}

R Documentation

Univariate conditional predictive cumulative distribution function

Description

This function serves as an inference tool for the MCMC output obtained using the function NMixMCMC. It computes (posterior predictive) estimates of univariate conditional cumulative distribution functions.

Usage

NMixPredCondCDFMarg(x, ...)

## Default S3 method:
NMixPredCondCDFMarg(x, icond, prob, scale, K, w, mu, Li, Krandom=FALSE, ...)

## S3 method for class 'NMixMCMC'
NMixPredCondCDFMarg(x, icond, prob, grid, lgrid=50, scaled=FALSE, ...)

## S3 method for class 'GLMM_MCMC'
NMixPredCondCDFMarg(x, icond, prob, grid, lgrid=50, scaled=FALSE, ...)

Arguments

`x`	an object of class `NMixMCMC` for `NMixPredCondCDFMarg.NMixMCMC` function. An object of class `GLMM_MCMC` for `NMixPredCondCDFMarg.GLMM_MCMC` function. A list with the grid values (see below) for `NMixPredCondCDFMarg.default` function.
`icond`	index of the margin by which we want to condition
`prob`	a numeric vector. If given then also the posterior pointwise quantiles of the conditional cdf's are computed for probabilities given by `prob`. These can be used to draw pointwise credible intervals.
`scale`	a two component list giving the `shift` and the `scale`. If not given, shift is equal to zero and scale is equal to one.
`K`	either a number (when `Krandom=FALSE`) or a numeric vector with the chain for the number of mixture components.
`w`	a numeric vector with the chain for the mixture weights.
`mu`	a numeric vector with the chain for the mixture means.
`Li`	a numeric vector with the chain for the mixture inverse variances (lower triangles only).
`Krandom`	a logical value which indicates whether the number of mixture components changes from one iteration to another.
`grid`	a list with the grid values for each margin in which the cdf should be evaluated. The value of `grid[[icond]]` determines the values by which we condition. If `grid` is not specified, it is created automatically using the information from the posterior summary statistics stored in `x`.
`lgrid`	a length of the grid used to create the `grid` if that is not specified.
`scaled`	if `TRUE`, the cdf of shifted and scaled data is summarized. The shift and scale vector are taken from the `scale` component of the object `x`.
`...`	optional additional arguments.

Value

An object of class NMixPredCondCDFMarg which has the following components:

`x`	a list with the grid values for each margin. The components of the list are named `x1`, ... or take names from `grid` argument.
`icond`	index of the margin by which we condition.
`cdf`	a list with the computed conditional cdf's for each value of `x[[icond]]`. Each `cdf[[j]]` is again a list with conditional cdf's for each margin given margin `icond` equal to `x[[icond]][j]`. The value of `cdf[[j]][[imargin]]` gives a value of a marginal cdf of the `imargin`-th margin at `x[[icond]][j]`.
`prob`	a value of the argument `prob`.
`qXX%`	if `prob` is given then there is one additional component named qXX%, e.g., q50% for each value of `prob` which has the same structure as the component `cdf` and keeps computed posterior pointwise quantiles.

There is also a plot method implemented for the resulting object.

Author(s)