dealWithLabelSwitching: Apply label switching algorithms

In fabMix: Overfitting Bayesian Mixtures of Factor Analyzers with Parsimonious Covariance and Unknown Number of Components

Apply label switching algorithms

Description

This functions is a wrapper for the label.switching package and applies the ECR and ECR.ITERATIVE.1 algorithms. The model may have the same variance of error terms per cluster or not.

Usage

dealWithLabelSwitching(sameSigma, x_data, outputFolder, q, burn, 
		z.true, compute_regularized_expression, Km)

Arguments

sameSigma	Logical value indicating whether the parameterization with the same error variance per cluster is used.
x_data	Data
outputFolder	Name of the folder where the fabMix function has saved its output
q	Number of factors
burn	Discard observations as burn-in period (optional).
z.true	An (optional) vector of cluster assignments which is considered as the groun-truth clustering of the data. Useful for direct comparisons against the real parameter values in simulated data.
compute_regularized_expression	Logical. Should regularized expression be computed?
Km	Number of components in the overfitted mixture model.

Value

The following files are produced in the output folder:

Author(s)

Panagiotis Papastamoulis

References

Papastamoulis, P. (2016). label.switching: An R Package for Dealing with the Label Switching Problem in MCMC Outputs. Journal of Statistical Software, 69(1), 1-24.

fabMix documentation built on May 29, 2024, 2:53 a.m.