Multivariate kernel density estimation

Multivariate kernel density estimation is a way to estimate the probability density of something that has multiple variables. For example, it might tell us the probability of a person being a certain age and having a certain income level. To use this method, we first collect samples that have multiple variables-- like age and income. Then we take the average of all of the samples with similar values. Finally, we use a "kernel" which is just a fancy way of saying a kind of mathematical formula, to calculate the probability that something has those values.