# Problem with COVARIANCE option in Data Analysis

1. ## Problem with COVARIANCE option in Data Analysis

Hi,

I am using Excel's Covariance option from the Data Analysis tools to produce a covariance matrix for a number of variables. I've noticed that the resulting matrix shows only one covariance per pair of variables, and leaves blank the cell at the other intersection of the variables. However, I would like the covariance to appear in both cells for each pair.

Is it possible to amend this?

Thanks!  Register To Reply

2. ## Analysis Data (Covariance)

Hello,

Remember that cov(x;y) is equal to cov(y;x).
What Analysis Data (Covariance) reports is a table with (example of 3 variables x;y;z) :

--------x------y------z
x cov(x;x)
y cov(x;y) cov(y;y)
z cov(x;z) Cov(y;z) Cov(z;z)

(You can get the same result using the function =COVAR(var1;var2) for each pair of matrix)

Then the first empty cell should have Cov(y;x) that as been reported as Cov(x;y).

If you wish no to see empty cells you have to force their contents with excel equality “function” after Analysis Data has been created.

Regards,

Emilio Caliandro  Register To Reply