logLik.ipriorMod: Obtain the log-likelihood and deviance of an I-prior model

In iprior: Regression Modelling using I-Priors

Description

This function calculates the log-likelihood value or deviance (twice the negative log-likelihood) for I-prior models. It works for both ipriorMod and ipriorKernel class objects.

Usage

## S3 method for class 'ipriorMod'
logLik(object, theta = NULL, ...)

## S3 method for class 'ipriorMod'
deviance(object, theta = NULL, ...)

## S3 method for class 'ipriorKernel'
logLik(object, theta = NULL, ...)

## S3 method for class 'ipriorKernel'
deviance(object, theta = NULL, ...)

Arguments

object	An object of class ipriorMod or ipriorKernel.
theta	(Optional) Evaluates the log-likelihood at theta.
...	Not used.

Details

For ipriorKernel objects, the log-likelihood or deviance is calculated at the default parameter values: scale parameters and error precision are equal to one, while hyperparameters of the kernels (e.g. Hurst index, lengthscale, etc.) are the default values (see here for details) or ones that has been specified. For ipriorMod objects, the log-likelihood or deviance is calculated at the last obtained value from the estimation method.

For both types of objects, it is possible to supply parameter values at which to calculate the log-likelihood/deviance. This makes estimating an I-prior model more flexible, by first loading the variables into an ipriorKernel object, and then using an optimiser such as optim. Parameters have been transformed so that they can be optimised unconstrained.

See Also

check_theta.

iprior documentation built on May 2, 2019, 3:21 a.m.