Some Information Theoretic Ideas Useful in Statistical Inference

In this paper we discuss four information theoretic ideas and present their implications to statistical inference: (1) Fisher information and divergence generating functions, (2) information optimum unbiased estimators, (3) information content of various statistics, (4) characterizations based on Fisher information. This paper was written while the first author was visiting the University of Cyprus, Department of Mathematics and Statistics.     

Information in Quantal Response Data and Random Censoring

In this paper we study interesting properties of Fisher and divergence type measures of information for quantal, complete and incomplete random censoring, and not censoring at all. It is shown that, while quantal random censoring is less expensive, it is less informative than complete random censoring. It is also shown that in experiments which are mixtures of quantal and complete random censoring, the information received from these experiments is a convex combination of quantal information and the information in complete random censoring. Finally, the "total information" property is studied, in which the information received by the uncensored experiment can be expressed as the sum of the information provided by random censoring and the loss of information due to censoring. The results for Fisher's measure of information are an extension of already known results to the multiparameter case. The investigation of the previous information properties for divergence type measures is a new element, as well as the comparison of byproducts of Fisher information matrices.     

Platinum-dihalide complexes with N-alkyl O-ethylthiocarbamates

Summary The thiocarbamic esters (L)ETC(EtOSCNHEt) and PTC (EtOSCNHPr) act as sulphur donors towards platinum halides, yielding the cis-[Pt(L)₂Cl₂], trans-[Pt(L)₂Br₂], [Pt(L)₃X]X (X = Cl or Br) and [Pt(L)₄]X₂ (X = Cl, Br or I) complexes. By addition of n-hexane to platinum chloride solutions in pure ligands the 16 adducts [Pt(L)₄]-Cl₂·2L have been isolated. The non-bonded ligand molecules are easily released to give the corresponding 14 complexes. The compounds have been characterized by elemental analysis and spectroscopy. The 14 and 16 complexes decompose in benzene to form the 13 species, except for [Pt(ETC)₄]I₂, which releases two ligand molecules to give trans-[Pt(ETC)₂I₂]. The 12 and 13 complexes have been tested for in vitro cytostatic activity against KB cells.     

Enantioselective synthesis of a mitosane core assisted by diversity-based catalyst discovery

[reaction: see text]. Synthesis of mitosane 1 in optically pure form is reported. A retrosynthetic plan that proceeds through racemic allylic alcohol 3 was carried out. This intermediate served as a test substrate for a rapid screen of a small library (152 members) of peptide-based kinetic resolution catalysts. Peptide 9 was found to effect kinetic resolution with k(rel) = 27. Alcohol (-)-3 was then converted to optically pure (-)-1 in eight steps.     

A Lattice Boltzmann study of non-newtonian flow in digitally reconstructed porous domains

In the present study, the Lattice Boltzmann Method (LBM) is applied to simulate the flow of non-Newtonian shear-thinning fluids in three-dimensional digitally reconstructed porous domains. The non-Newtonian behavior is embedded in the LBM through a dynamical change of the local relaxation time. The relaxation time is related to the local shear rate in such a way that the power law rheology is recovered. The proposed LBM is applied to the study of power-law fluids in ordered sphere packings and stochastically reconstructed porous domains. A linear relation is found between the logarithm of the average velocity and the logarithm of the body force with a curve slope approximately equal to the inverse power-law index. The validity of the LBM for the flow of shear thinning fluids in porous media is also tested by comparing the average velocity with the well known semi-empirical Christopher–Middleman correlation. Good agreement is observed between the numerical results and the Christopher–Middleman correlation, indicating that the LBM combined with digital reconstruction constitutes a powerful tool for the study of non-Newtonian flow in porous media.     

Randomized on-line algorithms and lower bounds for computing large independent sets in disk graphs

We study the on-line version of the maximum independent set problem, for the case of disk graphs which are graphs resulting from intersections of disks on the plane. In particular, we investigate whether randomization can be used to break known lower bounds for deterministic on-line independent set algorithms and present new upper and lower bounds.     

Pseudo-potentiostatic electrolysis by potential buffering induced by the oxygen evolution reaction

A new approach is proposed in order to perform electrochemical oxidation of organics by working under galvanostatic conditions with the potential ‘buffered’ by the competing side reaction of oxygen evolution (OER). According to this process the working potential is fixed by the nature of electrode material and is buffered during organics oxidation by the side reaction of OER. This principle has been used for the selective oxidation of some model organic compounds on Ti/IrO₂ anode.