Some remarks to multivariate regression model

Some remarks to problems of point and interval estimation, testing and problems of outliers are presented in the case of multivariate regression model. This work was supported by the Council of Czech Government J14/98:153100011.     

Possible Loss and Recovery of Gibbsianness¶During the Stochastic Evolution of Gibbs Measures

We consider Ising-spin systems starting from an initial Gibbs measure ν and evolving under a spin-flip dynamics towards a reversible Gibbs measure μ≠ν. Both ν and μ are assumed to have a translation-invariant finite-range interaction. We study the Gibbsian character of the measure νS(t) at time t and show the following: (1) For all ν and μ, νS(t) is Gibbs for small t. (2) If both ν and μ have a high or infinite temperature, then νS(t) is Gibbs for all t > 0. (3) If ν has a low non-zero temperature and a zero magnetic field and μ has a high or infinite temperature, then νS(t) is Gibbs for small t and non-Gibbs for large t. (4) If ν has a low non-zero temperature and a non-zero magnetic field and μ has a high or infinite temperature, then νS(t) is Gibbs for small t, non-Gibbs for intermediate t, and Gibbs for large t. The regime where μ has a low or zero temperature and t is not small remains open. This regime presumably allows for many different scenarios. Received: 26 April 2001 / Accepted: 10 October 2001     

Determination of lithium in wines by atomic absorption spectrometry

Lithium (10–150 ng ml^?1) in wine is determined by atomic absorption spectrometry by direct nebulization and after digestion with mixed acids. The results of methods are similar. Thirty-four wines from various Spanish provinces are analysed.     

Studies aimed at the synthesis of morphine V an economic approach to (±)-reticuline from 3,4-dihydropapaverine

Regioselective demethylation of 3,4-dihydropapaveraldine ($\text{2}$a) at 7 and 3' positions affords a properly substituted diphenolic key intermidiate ($\text{2}$d) for the synthesis of reticuline and N-norreticuline.     

Why and how to avoid standard kinetic equations I. Principles and band conduction problem

A review of ideas leading to full rejection of any finite or partially-infinite order kinetic equation linearized in external field is given on grounds of the time-convolution Generalized Master Equations (GME). By two examples (two-level and band conduction problem), it is shown how standard kinetic equations result from GME in the lowest order approximations which obscure, however, a direct correspondence with the Kubo linear response theory. Without approximations, on the other hand, the rigorous approach is shown to be fully equivalent with the Kubo results. It is argued and illustrated that usual technical simplicity and seeming physical lucidity of standard theories (connected with the presence of field-independent transfer or scattering rates in the fielddependent linearized theory) are just owing to structural features which are solely due to the lowest order approximations involved. These features (i.e. also the possibility of standard physical interpretation of kinetic phenomena) are proved to disappear completely as far as the theory goes properly to higher orders.     

Unavoidable Traces Of Set Systems

Sauer, Shelah, Vapnik and Chervonenkis proved that if a set system on n vertices contains many sets, then the set system has full trace on a large set. Although the restriction on the size of the groundset cannot be lifted, Frankl and Pach found a trace structure that is guaranteed to occur in uniform set systems even if we do not bound the size of the groundset. In this note we shall give three sequences of structures such that every set system consisting of sufficiently many sets contains at least one of these structures with many sets.     

Book rewiev

Howard Anton and Robert C. Busby, John Wiley & Sons, Inc., 2002.     

Magnetic poly(N‐isopropylacrylamide) microspheres by dispersion and inverse emulsion polymerization

The aim of this study was to develop novel thermally responsive polymer microspheres with magnetic properties. Dispersion and inverse emulsion copolymerization of N‐isopropylacrylamide (NIPAAm) and N,N′‐methylenebisacrylamide (MBAAm) was investigated in the presence of γ‐Fe₂O₃ nanoparticles. The resulting microspheres were characterized in terms of morphology, size, polydispersity, iron content, and temperature‐dependent swelling using optical microscopy, transmission electron microscopy, scanning electron microscopy, QELS, and AAS. The effects of several variables, such as the concentration of γ‐Fe₂O₃, MBAAm crosslinking agent, Span 80 surfactant, 2,2′‐azobis(2‐methyloctanenitrile) (AMON) initiator, and polymerization temperature on the properties of the microspheres were studied. Swelling and thermoresponsive behavior of the microspheres containing γ‐Fe₂O₃ nanoparticles were also investigated. The microspheres contained about 8 wt % of iron. The presence of magnetic nanoparticles and their concentration changes did not have any significant effect on the temperature sensitivity of the composites. The particles gradually shrink into an increasingly collapsed state when the temperature is raised to 40 °C since the increase in temperature weakens the hydration and PNIPAAm chains gradually become more hydrophobic, which leads to the collapse of the particles. © 2007 Wiley Periodicals, Inc. J Polym Sci Part A: Polym Chem 45: 5884–5898, 2007     

Arsenic determination in marine sediment using ultrasound for sample preparation.

This work deals with As determination in marine sediment using ultrasound for sample preparation. It is shown that As can be quantitatively extracted from marine sediment using 20% (v/v) HCl and sonication. The slurry is centrifuged and the analyte is determined in the supernatant by hydride generation atomic absorption spectrometry (HG AAS). A flow injection (FI) system is employed for hydride generation, with 0.5% (m/v) NaBH(4) used as reducdant and a 20% (v/v) HCl used as sample carrier. The limit of quantification is 1.6 microg g(-1) of As, which is based on 800 microl of sample solution and 0.200 g of sample mass in a volume of 50 mL. Certified and non certified marine sediment samples were analyzed; the results were in accordance with the certified or reference values. Speciation analysis by HPLC-ICP-MS showed that As(V) is the only detectable As species present in the supernatant of the centrifuged sample.