Suppose Y has a linear regression on X1, X2, but observations are only available on (Y, X1). If large scale data on (X1, X2) are available, which do not include Y, and if the regression of X2, given X1, is nonlinear, then one may estimate the regression coefficients of Y by using the proxy g(X1)...

Let X, Y be random vectors with values in d and 1, respectively, and denote by F(· x) the conditional distribution function of Y given X = x. It is well known that the kernel estimator of the regression functional [theta](x) := T(F(· x)), based on n independent replicates of (X, Y), has...

Bounds are obtained on the limiting size of the nominal level-[alpha] likelihood ratio test of independence in a r - c contingency table. The situations considered include sampling with both marginal totals random and with one margin fixed. Upper and lower bounds are obtained. The limiting size...

This work derives explicit kernel approximations for universal kriging predictors for a class of intrinsic random function models. This class of predictors is of particular interest because they are equivalent to the standard two-dimensional thin plate smoothing splines. By introducing a...

Let F and G be multivariate probability distribution functions, each with equal one dimensional marginals, such that there exists a sequence of constants an 0, n [set membership, variant] , with [formula] for all continuity points (x1, ..., xd) of G. The distribution function G is characterized...

Let {X1n}, ..., {Xkn} be k stationary Gaussian processes. Suppose H is a functional of k variables. We are interested in the asymptotic distribution of the sequence [formula] where AN are appropriate forming constants and assuming that the correlation matrix tends slowly to 0. The limit...

A recently proposed method of multiple frequency estimation for mixed-spectrum time series is analyzed. The so-called PF method is a procedure that combines the autoregressive (AR) representation of superimposed sinusoids with the idea of parametric filtering. The gist of the method is to...

In this note we prove a functional central limit theorem for LPQD processes, satisfying some assumptions on the covariances and the moment condition supj>=1EXj2+[rho] < [infinity] for some [rho] > 0.

Using Hoeffding's decomposition and truncation arguments we prove some theorems on the conxergence of the distribution of suitably normalized U-statistics to an [alpha]-stable limit distribution, 1 < [alpha] <= 2, under very weak moment conditions on the kernel function.

Let [mu](· ; [Sigma], G1) and [mu](· ; [Omega], G2) be elliptically contoured measures on k centered at 0, having scale parameters ([Sigma], [Omega]) and radial cdf's (G1, G2). Elliptical measures vm(·) and vM(·), depending on ([Sigma], [Omega], G1, G2), are constructed such that...