2
$\begingroup$

I'm trying to get an intuition as to why degrees of freedom is n - 1 when calculating sample covariance. This is what I found:

1) Start with 2n degrees of freedom from the bivariate data 2) Lose 2 degrees of freedom from calculating the means 3) Lose n-1 degrees of freedom from computing product derivations

In step 3, are the degrees of freedom being halved, or is n-1 being subtracted? What is the intuition of step 3?

$\endgroup$