Random Matrices: Theory and Applications

We consider the roots of uniformly chosen complex and real reciprocal polynomials of degree $N$ whose Mahler measure is bounded by a constant. After a change of variables, this reduces to a generalization of Ginibre’s complex and real ensembles of random matrices where the weight function (on the eigenvalues of the matrices) is replaced by the exponentiated equilibrium potential of the interval $[-2,2]$ on the real axis in the complex plane. In the complex (real) case, the random roots form a determinantal (Pfaffian) point process, and in both cases, the empirical measure on roots converges weakly to the arcsine distribution supported on $[-2,2]$. Outside this region, the kernels converge without scaling, implying among other things that there is a positive expected number of outliers away from $[-2,2]$. These kernels as well as the scaling limits for the kernels in the bulk $(-2,2)$ and at the endpoints $\{-2,2\}$ are presented. These kernels appear to be new, and we compare their behavior with related kernels which arise from the (non-reciprocal) Mahler measure ensemble of random polynomials as well as the classical Sine and Bessel kernels.

A popular approach, generalized estimating equations (GEE), has been applied to the multivariate accelerated failure time (AFT) model of the clustered and censored data. However, this method needs to estimate the correlation parameters and calculate the inverse of the correlation matrix. Meanwhile, the efficiency of the parameter estimators is low when the correlation structure is misspecified and/or the marginal distribution is heavy-tailed. This paper proposes using the quadratic inference functions (QIF) with a mixture correlation structure to estimate the coefficients in the multivariate AFT model, which can avoid estimating the correlation parameters and computing the inverse matrix of the correlation matrix. Moreover, the estimator derived from the QIF is consistent and asymptotically normal. Simulation studies indicate that the proposed method outperforms the method based on GEE when the marginal distribution has a heavy tail. Finally, the proposed method is used to analyze a real dataset for illustration.

Change-point detection is an integral component of statistical modeling and estimation. For high-dimensional data, classical methods based on the Mahalanobis distance are typically inapplicable. We propose a novel testing statistic by combining a modified Euclidean distance and an extreme statistic, and its null distribution is asymptotically normal. The new method naturally strikes a balance between the detection abilities for both dense and sparse changes, which gives itself an edge to potentially outperform existing methods. Furthermore, the number of change-points is determined by a new Schwarz’s information criterion together with a pre-screening procedure, and the locations of the change-points can be estimated via the dynamic programming algorithm in conjunction with the intrinsic order structure of the objective function. Under some mild conditions, we show that the new method provides consistent estimation with an almost optimal rate. Simulation studies show that the proposed method has satisfactory performance of identifying multiple change-points in terms of power and estimation accuracy, and two real data examples are used for illustration.

In this paper, we highlight the role played by orthogonal and symplectic Harish-Chandra integrals in the study of real-valued matrix product ensembles. By making use of these integrals and the matrix-valued Fourier-Laplace transform, we find the explicit eigenvalue distributions for particular Hermitian anti-symmetric matrices and Hermitian anti-self dual matrices, involving both sums and products. As a consequence of these results, the eigenvalue probability density function of the random product structure $X_M\cdots X_1(iA)X_1^T\cdots X_M^T$, where each $X_i$ is a standard real Gaussian matrix, and $A$ is a real anti-symmetric matrix can be determined. For $M=1$ and $A$ the bidiagonal anti-symmetric matrix with 1’s above the diagonal, this reclaims results of Defosseux. For general $M$, and this choice of $A$, or $A$ itself a standard Gaussian anti-symmetric matrix, the eigenvalue distribution is shown to coincide with that of the squared singular values for the product of certain complex Gaussian matrices first studied by Akemann et al. As a point of independent interest, we also include a self-contained diffusion equation derivation of the orthogonal and symplectic Harish-Chandra integrals.