A class of bivariate rank tests are developed for the two-sample problem of testing equality of distributions against certain one-sided alternatives. These tests are the nonparametric analogs of a normal theory test proposed by Schaafsma and Smid. These tests are shown to be unbiased and the...

A parametric method for dividing a heterogeneous multivariate population into components is proposed. The method includes the following operations: (1) The mixed population is divided into two parts by a linear discriminant function with arbitrary coefficients; (2) The parameters of both parts...

Stochastic integrals are constructed with values in a compact Riemann manifold from a continuous martingale integrator that is given in the tangent space of the initial point of the stochastic integral and from a stochastic tensor field of linear endomorphisms of the tangent bundle. The...

A semigroup approximation theorem is used to prove the convergence of approximate likelihood ratios.

The quadratic variation of functionals of the two-parameter Wiener process of the form f(W(s, t)) is investigated, where W(s, t) is the standard two-parameter Wiener process and f is a function on the reals. The existence of the quadratic variation is obtained under the condition that f' is...

The present paper is devoted to some remarks and alterations concerning our preceding articles [1-3].

A multiple time series is defined as the sum of an autoregressive process on a line and independent Gaussian white noise on a hyperplane that goes through the origin and intersects the line at a single point. This process is a multiple autoregressive time series in which the regression matrices...