BIC: Bayesian Information Criterion

In arf3DS4: Activated Region Fitting, fMRI data analysis (3D).

Description

BIC calculates the Bayesian Information Criterion (model fit) for a valid ARF model. BIC requires a valid (converged) ARF model (model).

Usage

BIC(arfmodel, options = loadOptions(arfmodel))

Arguments

arfmodel	A fitted (and valid) ARF model object of class model.
options	An "options" object. The options object belonging to the ARF model is loaded by default.

Details

BIC calculates the BIC value using the number of brain voxels (Set by the model@mask slot). Without constants the BIC equals:

BIC = ln(S(theta)) + p * ln(n)

where p is the number of parameters in the spatial model, n is the number of brain voxels, and S(theta) denotes the minimum of the objective function.

Value

Returns an object of class "model" with the slot model@fit[1] set to the BIC value.

Author(s)

Wouter D. Weeda - [e-mail]

See Also

RMSEA, model, options

arf3DS4 documentation built on May 2, 2019, 5:16 p.m.