In a multiparameter setting, considering a very large class of tests it is seen that under contiguous alternatives, unlike in the one-parameter case, identity of power up to the first order may not imply that up to the second order. It is, therefore, possible to discriminate among tests in terms...

A multivariate concordance ordering is defined by the ordering of the multivariate distribution functions and corresponding survival functions. Multivariate versions of Blomqvist's q, Kendall's [tau], and Spearman's [varrho], that are increasing relative to the concordance ordering, are obtained.

It is assumed that we observe one realization of an r dimensional counting process with intensities that are products of predictable and observable weight processes, a common function of time, and predictable functions that depend on an unknown parameter [theta]. Given that the realization...

An extension of the "prior density for path" (Onsager-Machlup functional) is defined and shown to exist for Gaussian fields generated by solutions of elliptic PDEs driven by white noise. This functional is then used to define and solve the MAP estimation of such fields observed via nonlinear...

Assume X = (X1, ..., Xp)' is a normal mixture distribution with density w.r.t. Lebesgue measure, , where [Sigma] is a known positive definite matrix and F is any known c.d.f. on (0, [infinity]). Estimation of the mean vector under an arbitrary known quadratic loss function Q([theta], a) = (a -...

Let (X, Y) be a random vector in the plane and denote by m(x) = (YX = x) the corresponding regression function. We show that the bootstrap approximation for the distribution of a smoothed nearest neighbor estimate of m(x) is valid. Also we compare, by Monte Carlo, confidence intervals which are...

We prove two mixed limit theorems for pattern synthesis, one for linear and one for cyclic connection graphs. This extends an earlier result for linear graphs in that it shows that the acceptor function need only satisfy weak conditions for the limits to exist.

This paper introduces a concept of a general ARMA model. The Wold's decomposition is extended to a class of stochastic processes without moment conditions. There are given regularity conditions under which there exists a purely nondeterministic solution of ARMA equation. The prediction problem...

A complete characterization of multivariate random variables with minimum L2 Wasserstein-distance is proved by means of duality theory and convex analysis. This characterization allows to determine explicitly the optimal couplings for several multivariate distributions. A partial solution of...

For statistical experiments dual pairs of Riesz spaces are introduced which are related to spaces defined by Pitcher in connection with compact experiments. Likewise there are relations to enlargements of Le Cam's M-space defined by Torgersen in a study on complete sufficient statistics and...