İki kovaryans matrisi arasındaki benzerlik veya mesafenin ölçülmesi


28

İki simetrik kovaryans matrisi arasında benzerlik veya mesafe ölçütleri var mı (ikisi de aynı boyutlara sahip)?

Burada, iki olasılık dağılımının KL farklılığına veya matrislere uygulanmadıkları sürece vektörler arasındaki Öklid mesafesine analogları düşünüyorum. Bir kaç benzerlik ölçümü olacağını hayal ediyorum.

İdeal olarak, iki kovaryans matrisinin aynı olduğu gibi boş hipotezi test etmek istiyorum.


3
the answers to this question: quant.stackexchange.com/q/121/108 may be of some use.
shabbychef

2
excellent question and answer on the link - thanks - yes this is where I was going :)
Ram Ahluwalia

Yanıtlar:


21

You can use any of the norms ABp (see Wikipedia on a variety of norms; note that the square-root of the sum of squared distances, i,j(aijbij)2, is called Frobenius norm, and is different from L2 norm, which is the square root of the largest eigenvalue of (AB)2, although of course they would generate the same topology). The K-L distance between the two normal distributions with the same means (say zero) and the two specific covariance matrices is also available in Wikipedia as 12[tr(A1B)ln(|B|/|A|)].

Edit: if one of the matrices is a model-implied matrix, and the other is the sample covariance matrix, then of course you can form a likelihood ratio test between the two. My personal favorite collection of such tests for simple structures is given in Rencher (2002) Methods of Multivariate Analysis. More advanced cases are covered in covariance structure modeling, on which a reasonable starting point is Bollen (1989) Structural Equations with Latent Variables.


i have a problem with 1/2(tr(A1B)log(|B|/|A|)): it doesn't give the same value if you permute A and B ( a real distance should be symmetric).
user603

i have a problem with (AB)2: it is not affine equivariant (if you rotate the matrices, there distance changes!). Furthermore, you should somehow scale your matrices (they might be measured in very different units), also, it is only natural to require that the distance between two covariance matrices be the same as the distance between the corresponding correlation matrices: so I suggest (Adet(A)1/pBdet(B)1/p)2.
user603

2
First, K-L is not a real distance, and that's a well known fact. Second, if the matrices are measured in different units, they cannot be equal.
StasK

Is K-L distance similar to likelihood ratio, or are they related?
hashmuke

7

Denote Σ1 and Σ2 your matrices both of dimension p.

  1. Cond number: log(λ1)log(λp) where λ1 (λp) is the largest (smallest) eigenvalue of Σ, where Σ is defined as: Σ:=Σ11/2Σ2Σ11/2

Edit: I edited out the second of the two proposals. I think I had misunderstood the question. The proposal based on condition numbers is used in robust statistics a lot to assess quality of fit. An old source I could find for it is:

Yohai, V.J. and Maronna, R.A. (1990). The Maximum Bias of Robust Covariances. Communications in Statistics–Theory and Methods, 19, 3925–2933.

I had originally included the Det ratio measure:

  1. Det ratio: log(det(Σ)/det(Σ2)det(Σ1)) where Σ=(Σ1+Σ2)/2.

which would be the Bhattacharyya distance between two Gaussian distributions having the same location vector. I must have originally read the question as pertaining to a setting where the two covariances were coming from samples from populations assumed to have equal means.



Sitemizi kullandığınızda şunları okuyup anladığınızı kabul etmiş olursunuz: Çerez Politikası ve Gizlilik Politikası.
Licensed under cc by-sa 3.0 with attribution required.