This note contains a transparent presentation of the matrix Haffian. A basic theorem links this matrix and the differential ofthe matrix function under investigation, viz ∇F(X) and dF(X). Frequent use is being made of matrix derivatives as developed by Magnus and Neudecker.
A matrix derivation of a well-known representation theorem for (tr A) is given, which is the solution of a restricted maximization problem. The paper further gives a solution of the corresponding restricted minimization problem.
The main aim is to estimate the noncentrality matrix of a noncentral Wishart distribution. The method used is Leung's but generalized to a matrix loss function. Parallelly Leung's scalar noncentral Wishart identity is generalized to become a matrix identity. The concept of Löwner partial ordering of symmetric matrices is used.
A simple proof is given for a theorem by Milliken and Akdeniz (1977) about the difference of the Moore-Penrose inverses of two positive semi-definite matrices.
This paper gives a generalization of results presented by ten Berge, Krijnen,Wansbeek & Shapiro. They examined procedures and results as proposed by Anderson & Rubin, McDonald, Green and Krijnen, Wansbeek & ten Berge.We shall consider the same matter, under weaker rank assumptions. We allow some moments, namely the variance Ω of the observable scores vector and that of the unique factors, Ψ, to be singular. We require T' Ψ T > 0, where T Λ T' is a Schur decomposition of Ω. As...
The article establishes relationships between the matrix derivatives of F with respect to X as introduced by von Rosen (1988), Kollo and von Rosen (2000) and the Magnus-Neudecker (1999) matrix derivative. The usual transformations apply and the Moore-Penrose inverse of the duplication matrix is used. Both X and F have the same dimension.
In this paper we revisit Haff's seminal work on the matrix Haffian as we proposed to call it. We review some results, and give new derivations. Use is made of the link between the matrix Haffian ∇F and the differential of the matrix function, dF.
In this note a uniform transparent presentation of the scalar Haffian will be given. Some well-known results will be generalized. A link will be established between the scalar Haffian and the derivative matrix as developed by Magnus and Neudecker.
We use Haff's fundamental identity to express the expectation of S in lower-order terms, where S follows the central Wishart distribution.
In this paper the Kronecker and inner products of mean vectorsof two different populations are considered. Using the generalized jackknife approach, estimators for these products are constructed which turn out to be unbiased, provided one can assume multinormal distribution.
Page 1