# how do we plot a bivariate normal distribution from one side?

67 views (last 30 days)
ektor on 19 Nov 2016
Edited: Marina Kiseleva on 4 Sep 2018
Dear all
I plot the following bivariate distribution
mu = [0 0];
Sigma = [.25 .3; .3 1];
x1 = -3:.2:3; x2 = -3:.2:3;
[X1,X2] = meshgrid(x1,x2);
F = mvnpdf([X1(:) X2(:)],mu,Sigma);
F = reshape(F,length(x2),length(x1));
surf(x1,x2,F);
caxis([min(F(:))-.5*range(F(:)),max(F(:))]);
axis([-3 3 -3 3 0 .4])
xlabel('x1'); ylabel('x2'); zlabel('Probability Density');
My question is how do I plot the joint density from the vantage point of x1 or x2? So I want to obtain a 2D graph that shows x1 (or x2) on the x-axis and the density values on the y-axis
Any help is greatly appreciated.

Marina Kiseleva on 4 Sep 2018
Edited: Marina Kiseleva on 4 Sep 2018
You can plot the marginal distribution of x or y separately, using whatever variance and mean corresponds to it (page 4 of this link ).
For you, I think x1 has a sigma^2 of 0.25, and a mean of 0, so you can plot it like:
x = -3:.2:3;
density = normpdf(x, 0, sqrt(0.25));
plot(x, density);