where Y is an n-vector of responses, X is the n (k+1) full-rank matrix of xed predictor variables with ith row x0i = (xi0; xi1; : : : ; xik), xi0 = 1, = ( 0; : : : ; k) 0 is a (k+1)-vector of regression coe cients, and is an n-vector of random errors that is assumed to have a multivariate normal distribution with zero mean and precision matrix I. Following the notation of Aitchison and Dunsmore...

This paper considers methods for estimating the slope coe¢ cients in large panel data models that are robust to the presence of various forms of error cross section dependence. It introduces a general framework where error cross section dependence may arise because of unobserved common e¤ects and/or error spillover e¤ects due to spatial or other forms of local dependencies. Initially, this pape...

In standard wavelet methods, the empirical wavelet coe cients are thresholded term by term, on the basis of their individual magnitudes. Information on other coe cients has no in uence on the treatment of particular coe cients. We propose and investigate a wavelet shrinkage method that incorporates information on neighboring coe cients into the decision making. The coe cients are considered in ...

Tests for speeding up the determination of the Bernstein enclosure of the range of a multivariate polynomial and a rational function over a box and a simplex are presented. In the polynomial case, this enclosure is the interval spanned by the minimum and the maximum of the Bernstein coe cients which are the coe cients of the polynomial with respect to the tensorial or simplicial Bernstein basis...

This paper considers the estimation of coe cients in a linear regression model with missing obser vations in the independent variables and introduces a modi cation of the standard rst order regression method for imputation of missing values The modi cation provides stochastic values for imputation and as an extension makes use of the principle of weighted mixed regression The proposed proce dur...

We consider inference about a scalar coe¢ cient in a linear regression model. One previously considered approach to dealing with many controls imposes sparsity, that is it assumed known that nearly all control coe¢ cients are zero. We instead impose a bound on a weighted sum of squared control coe¢ cients, which is interpretable as a bound on the sample variation in the dependent variable induc...

The exoelectric e ect provides a linear coupling between electric polarization and orientational deformation in liquid crystals. It in uences many electrooptical phenomena and it is used in some bistable nematic devices. A statistical theory of dipole exoelectric polarization in biaxial nematic liquid crystals is used to calculate temperature dependence of order parameters, elastic constants, a...

A lossless image compression algorithm based on adaptive subband decomposition is proposed. The subband decomposition is achieved by a two-channel LMS adaptive "lter bank. The resulting coe$cients are lossy coded "rst, and then the residual error between the lossy and error-free coe$cients is compressed. The locations and the magnitudes of the nonzero coe$cients are encoded separately by an hie...

In this paper, the performance of several algorithms for the quantization of the mel-generalized cepstral coe cients is studied. First, the objective and subjective performance of two-stage vector quantization (VQ) is measured. It is shown that subjective quality for the mel-generalized cepstral coe cients is higher than that for LSP. Secondly, interframe prediction is introduced in the encodin...

This paper proposes a method of discovering some kinds of di erential equations with interval coe cients, which characterize or explain numerical data obtained by scienti c observations and experiments. Such numerical data inevitably involve some ranges of errors, and hence they are represented by closed intervals in this paper. Based on these intervals, we design some interval inclusions which...