A weak law of large numbers for the sample covariance matrix.
In this paper, we consider a symmetric α-stable p-sub-stable two-dimensional random vector. Our purpose is to show when the function is a characteristic function of such a vector for some p and α. The solution of this problem we can find in [3], in the language of isometric embeddings of Banach spaces. Our proof is based on simple properties of stable distributions and some characterization given in [4].
The problem of estimating the probability is considered when represents a multivariate stochastic input of a monotonic function . First, a heuristic method to bound , originally proposed by de Rocquigny (2009), is formally described, involving a specialized design of numerical experiments. Then a statistical estimation of is considered based on a sequential stochastic exploration of the input space. A maximum likelihood estimator of build from successive dependent Bernoulli data is defined...
By analogy to the real case established by Matusita (1955) we introduce the concept of affinity between two complex distribution functions. We also establish a concrete expression for the affinity between two complex k-variate normal distributions when the covariance matrices assume a special form. Generalizations of these results are presented and the expressions here obtained are compared with those obtained by Matusita (1966, 1967) relative to the affinity between real k-variate normal distributions....