gmm: Returns a Gaussian Mixture Model

In KSD: Goodness-of-Fit Tests using Kernelized Stein Discrepancy

Description

Returns a Gaussian Mixture Model

Usage

gmm(nComp = NULL, mu = NULL, sigma = NULL, weights = NULL, d = NULL)

Arguments

nComp	(scalar) : number of components
mu	(d by k): mean of each component
sigma	(d by d by k): covariance of each component
weights	(1 by k) : mixing weight of each proportion (optional)
d	: number of dimensions of vector (optional)

Value

model : A Gaussian Mixture Model generated from the given parameters

Examples

# Default 1-d gaussian mixture model
model <- gmm()

# 1-d Gaussian mixture model with 3 components
model <- gmm(nComp = 3)

# 3-d Gaussian mixture model with 3 components, with specified mu,sigma and weights
mu <- matrix(c(1,2,3,2,3,4,5,6,7),ncol=3)
sigma <- array(diag(3),c(3,3,3))
model <- gmm(nComp = 3, mu = mu, sigma=sigma, weights = c(0.2,0.4,0.4), d = 3)

Example output

KSD documentation built on Jan. 13, 2021, 8:39 a.m.