Joint Probability

I have a bunch of paired data (x,y) for which I would like to determine the joint probability density. I can easily find the marginal densities fx(x) and fy(y)and plan to do so using kernels (ksdensity). Any suggestions on finding the joint density fxy(x,y)or one of the conditional densities, fx(x|y) or fy(y|x), using the marginal densities?

My assumption is not the trivial solution when x and y are independent.

I understand the concepts but am struggling with the code.

Answer 1

[the cyclist]

The following entry in the File Exchange does 2-d kernel density esimation:

http://www.mathworks.com/matlabcentral/fileexchange/17204-kernel-density-estimation

I have not used it myself, but it is highly rated.

[Michael]

Thanks ! Looks like just what I need.