0
$\begingroup$

I am developing a classification task where I generate a gaussian distribution (its mean and standard deviation) from a set of 3-dimensional data. My question is: would the classifier give same outputs if I use three uni variate normal distributions or one 3-dimensional multivariate distribution? When getting the probability of a test point belonging to either the 3D distribution or the three separate distributions, would the number be the same?

$\endgroup$

1 Answer 1

1
$\begingroup$

A 3-d multivariate distribution would be the same as the 3 independent 1-d distributions if, you guessed, the dimensions are statistically independent of each other. If they are correlated, then you have to introduce that correlation one way or another.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.