Simulate Data from Gaussian Mixture Model

This example shows how to simulate data from a Gaussian mixture model (GMM) using a fully specified gmdistribution object and the random function.

Create a known, two-component GMM object.

mu = [1 2;-3 -5];
sigma = cat(3,[2 0;0 .5],[1 0;0 1]);
p = ones(1,2)/2;
gm = gmdistribution(mu,sigma,p);

Plot the contour of the pdf of the GMM.

gmPDF = @(x,y) arrayfun(@(x0,y0) pdf(gm,[x0 y0]),x,y);
fcontour(gmPDF,[-10 10]);
title('Contour lines of pdf');

Generate 1000 random variates from the GMM.

rng('default') % For reproducibility
X = random(gm,1000);

Plot the variates with the pdf contours.

hold on
scatter(X(:,1),X(:,2),10,'.') % Scatter plot with points of size 10
title('Contour lines of pdf and Simulated Data')