Find Covariance and Correlation of Joint Probability Distribution in Python

Question

If I'm given a joint distribution of 2 random variables say A and B, how would I find the covariance of A,B? (I have known to calculate E_X, E_Y, E_XY and apply formula, what I want to find library that calculate directly Cov(X,Y) without E_X,E_Y..).
Joint distribution:

X|Y 1 3 5
1  0.1 0.2 0.3
4  0.2 0.05 0.15

There might be a library which implements a covariance function for discrete variables. However, it seems likely that it would be simpler to just compute covariance directly from the definition -- it is a summation over all the possible values of X and Y, and there are only 6 of those. — Robert Dodier, May 13 '23 at 16:53

score 0 · Answer 1 · answered May 12 '23 at 20:30

0

Do you mean sth like: np.cov()?

check:

import numpy as np

answered May 12 '23 at 20:30

Mazur Ekaterina

56
3

If create a = np.array([0.1,0.2,0.3,0.2,0.05,0.15]).reshape(2,3), np.cov(a) doesn't return right answer. – NamNguyen May 12 '23 at 20:55
can you try transpose it before passing it to the function? np.cov(a.T) – Mazur Ekaterina May 13 '23 at 08:47
I tested it, I think when give this joint distribution we'll do by calculate E_X, E_Y, E_XY, only when give two array this time we use np.cov. Thank you. – NamNguyen May 14 '23 at 02:20

Find Covariance and Correlation of Joint Probability Distribution in Python

1 Answers1