Band 59, Heft 5

Flaminio and Montagna recently introduced state MV-algebras as MV-algebras with an internal notion of a state. The present authors gave a stronger version of state MV-algebras, called state-morphism MV-algebras. We present some classes of state-morphism MV-algebras like local, simple, semisimple state-morphism MV-algebras, and state-morphism MV-algebras with retractive ideals. Finally, we describe state-morphism operators on m-free generated MV-algebras, m < ∞.

The method used in nonlinear regression is most of the time the nonlinear squares. If the nonlinearity of the model is not too strong, it is possible to linearize the model and to use the linear statistical theory which is more simple. The question is under which condition this can be done. If the linearized model is regular such criteria were found. To find a solution for singular models is the aim of the paper.

The paper deals a class of rank based procedures for detection of changes with adaptively chosen scores. This is a certain continuation of the paper Antoch et al (2008). The limit behavior of the test procedures is studied both under the null as well as under a general class of alternatives. Accompanying simulation study focuses on various alternatives which are often met in practice.

The exact distribution of the APLE statistic for testing spatial dependencies is derived. Examples are given to compare with the more common Moran’s $$ \mathcal{I} $$ statistic.

A test of the equality of the first h eigenvectors of covariance matrices of several populations is constructed without the assumption that the sampled distributions are Gaussian. It is proved that the test statistic is asymptotically chi-square distributed. In this general setting, an explicit formula for column space of the asymptotic covariance matrix of the sample eigenvectors is derived and the rank of this matrix is computed. An essential assumption in deriving the asymptotic distribution of the presented test statistic is the existence of the finite fourth moments and the simplicity of the h largest eigenvalues of population covariance matrices, which makes possible to use the formulas for derivatives of eigenvectors of symmetric matrices.

Many nonlinear models as e.g. models of chemical reactions are described by systems of differential equations which have no explicit solution. In such cases the statistical analysis is much more complicated than for nonlinear models with explicitly given response functions. Numerical approaches need to be applied in place of explicit solutions. This paper describes how the analysis can be done when the response function is only implicitly given by differential equations. It is shown how the unknown parameters can be estimated and how these estimations can be applied for model discrimination and for deriving optimal designs for future research. The methods are demonstrated with a chemical reaction catalyzed by the enzyme Benzaldehyde lyase.

We consider the design of c-optimal experiments for the estimation of a scalar function h(θ) of the parameters θ in a nonlinear regression model. A c-optimal design ξ* may be singular, and we derive conditions ensuring the asymptotic normality of the Least-Squares estimator of h(θ) for a singular design over a finite space. As illustrated by an example, the singular designs for which asymptotic normality holds typically depend on the unknown true value of θ, which makes singular c-optimal designs of no practical use in nonlinear situations. Some simple alternatives are then suggested for constructing nonsingular designs that approach a c-optimal design under some conditions.

We consider the problem of making statistical inference about the mean of a normal distribution based on a random sample of quantized (digitized) observations. This problem arises, for example, in a measurement process with errors drawn from a normal distribution and with a measurement device or process with a known resolution, such as the resolution of an analog-to-digital converter or another digital instrument. In this paper we investigate the effect of quantization on subsequent statistical inference about the true mean. If the standard deviation of the measurement error is large with respect to the resolution of the indicating measurement device, the effect of quantization (digitization) diminishes and standard statistical inference is still valid. Hence, in this paper we consider situations where the standard deviation of the measurement error is relatively small. By Monte Carlo simulations we compare small sample properties of the interval estimators of the mean based on standard approach (i.e. by ignoring the fact that the measurements have been quantized) with some recently suggested methods, including the interval estimators based on maximum likelihood approach and the fiducial approach. The paper extends the original study by Hannig et al. (2007).