- #1
anja.ende
- 5
- 0
Hello,
The Mahalanobis distance or rather its square is defined as :
[itex](X-\mu)^2/\Sigma[/itex] which is then written as
[itex](X-\mu)^{T} Ʃ^{-1}(X-\mu)[/itex]
Ʃ is the covariance matrix. My silly question is why is the sigma placed in the middle of the dot product of the (X-μ) vector with itself. I am sure this makes sense mathematically (this reduces the output to a scalar) but I would like to know the intuitive reason behind it.
Thanks a lot!
Anja
The Mahalanobis distance or rather its square is defined as :
[itex](X-\mu)^2/\Sigma[/itex] which is then written as
[itex](X-\mu)^{T} Ʃ^{-1}(X-\mu)[/itex]
Ʃ is the covariance matrix. My silly question is why is the sigma placed in the middle of the dot product of the (X-μ) vector with itself. I am sure this makes sense mathematically (this reduces the output to a scalar) but I would like to know the intuitive reason behind it.
Thanks a lot!
Anja