Bayesian nonlinear regression models with scale mixtures of skew-normal distributions: Estimation and case influence diagnostics

The purpose of this paper is to develop a Bayesian analysis for nonlinear regression models under scale mixtures of skew-normal distributions. This novel class of models provides a useful generalization of the symmetrical nonlinear regression models since the error distributions cover both skewness and heavy-tailed distributions such as the skew-t, skew-slash and the skew-contaminated normal distributions. The main advantage of these class of distributions is that they have a nice hierarchical representation that allows the implementation of Markov chain Monte Carlo (MCMC) methods to simulate samples from the joint posterior distribution. In order to examine the robust aspects of this flexible class, against outlying and influential observations, we present a Bayesian case deletion influence diagnostics based on the Kullback-Leibler divergence. Further, some discussions on the model selection criteria are given. The newly developed procedures are illustrated considering two simulations study, and a real data previously analyzed under normal and skew-normal nonlinear regression models. (C) 2010 Elsevier B.V. All rights reserved.

Invariants of binary differential equations

In this paper, we study binary differential equations a(x, y)dy (2) + 2b(x, y) dx dy + c(x, y)dx (2) = 0, where a, b, and c are real analytic functions. Following the geometric approach of Bruce and Tari in their work on multiplicity of implicit differential equations, we introduce a definition of the index for this class of equations that coincides with the classical Hopf`s definition for positive binary differential equations. Our results also apply to implicit differential equations F(x, y, p) = 0, where F is an analytic function, p = dy/dx, F (p) = 0, and F (pp) not equal aEuro parts per thousand 0 at the singular point. For these equations, we relate the index of the equation at the singular point with the index of the gradient of F and index of the 1-form omega = dy -aEuro parts per thousand pdx defined on the singular surface F = 0.

An Information Theory framework for two-stage binary image operator design

The design of translation invariant and locally defined binary image operators over large windows is made difficult by decreased statistical precision and increased training time. We present a complete framework for the application of stacked design, a recently proposed technique to create two-stage operators that circumvents that difficulty. We propose a novel algorithm, based on Information Theory, to find groups of pixels that should be used together to predict the Output Value. We employ this algorithm to automate the process of creating a set of first-level operators that are later combined in a global operator. We also propose a principled way to guide this combination, by using feature selection and model comparison. Experimental results Show that the proposed framework leads to better results than single stage design. (C) 2009 Elsevier B.V. All rights reserved.

Multilevel Training of Binary Morphological Operators

The design of binary morphological operators that are translation-invariant and locally defined by a finite neighborhood window corresponds to the problem of designing Boolean functions. As in any supervised classification problem, morphological operators designed from a training sample also suffer from overfitting. Large neighborhood tends to lead to performance degradation of the designed operator. This work proposes a multilevel design approach to deal with the issue of designing large neighborhood-based operators. The main idea is inspired by stacked generalization (a multilevel classifier design approach) and consists of, at each training level, combining the outcomes of the previous level operators. The final operator is a multilevel operator that ultimately depends on a larger neighborhood than of the individual operators that have been combined. Experimental results show that two-level operators obtained by combining operators designed on subwindows of a large window consistently outperform the single-level operators designed on the full window. They also show that iterating two-level operators is an effective multilevel approach to obtain better results.

Perfect Simulation of a Coupling Achieving the (d)over-bar-distance Between Ordered Pairs of Binary Chains of Infinite Order

We explicitly construct a stationary coupling attaining Ornstein`s (d) over bar -distance between ordered pairs of binary chains of infinite order. Our main tool is a representation of the transition probabilities of the coupled bivariate chain of infinite order as a countable mixture of Markov transition probabilities of increasing order. Under suitable conditions on the loss of memory of the chains, this representation implies that the coupled chain can be represented as a concatenation of i.i.d. sequences of bivariate finite random strings of symbols. The perfect simulation algorithm is based on the fact that we can identify the first regeneration point to the left of the origin almost surely.

Multivariate measurement error models based on scale mixtures of the skew-normal distribution

Scale mixtures of the skew-normal (SMSN) distribution is a class of asymmetric thick-tailed distributions that includes the skew-normal (SN) distribution as a special case. The main advantage of these classes of distributions is that they are easy to simulate and have a nice hierarchical representation facilitating easy implementation of the expectation-maximization algorithm for the maximum-likelihood estimation. In this paper, we assume an SMSN distribution for the unobserved value of the covariates and a symmetric scale mixtures of the normal distribution for the error term of the model. This provides a robust alternative to parameter estimation in multivariate measurement error models. Specific distributions examined include univariate and multivariate versions of the SN, skew-t, skew-slash and skew-contaminated normal distributions. The results and methods are applied to a real data set.

Framework for Skew-Probit Links in Binary Regression

We review several asymmetrical links for binary regression models and present a unified approach for two skew-probit links proposed in the literature. Moreover, under skew-probit link, conditions for the existence of the ML estimators and the posterior distribution under improper priors are established. The framework proposed here considers two sets of latent variables which are helpful to implement the Bayesian MCMC approach. A simulation study to criteria for models comparison is conducted and two applications are made. Using different Bayesian criteria we show that, for these data sets, the skew-probit links are better than alternative links proposed in the literature.

Bayesian density estimation using Skew Student-t-Normal mixtures

We present a Bayesian approach for modeling heterogeneous data and estimate multimodal densities using mixtures of Skew Student-t-Normal distributions [Gomez, H.W., Venegas, O., Bolfarine, H., 2007. Skew-symmetric distributions generated by the distribution function of the normal distribution. Environmetrics 18, 395-407]. A stochastic representation that is useful for implementing a MCMC-type algorithm and results about existence of posterior moments are obtained. Marginal likelihood approximations are obtained, in order to compare mixture models with different number of component densities. Data sets concerning the Gross Domestic Product per capita (Human Development Report) and body mass index (National Health and Nutrition Examination Survey), previously studied in the related literature, are analyzed. (c) 2008 Elsevier B.V. All rights reserved.

Automorphism Groups of Generalized (Binary) Icosahedral, Tetrahedral and Octahedral Groups

Let G be any of the (binary) icosahedral, generalized octahedral (tetrahedral) groups or their quotients by the center. We calculate the automorphism group Aut(G).

ON SPECIALITY OF BINARY-LIE ALGEBRAS

In the present work, binary-Lie, assocyclic, and binary (-1,1) algebras are studied. We prove that, for every assocyclic algebra A, the algebra A(-) is binary-Lie. We find a simple non-Malcev binary-Lie superalgebra T that cannot be embedded in A(-s) for an assocyclic superalgebra A. We use the Grassmann envelope of T to prove the similar result for algebras. This solve negatively a problem by Filippov (see [1, Problem 2.108]). Finally, we prove that the superalgebra T is isomorphic to the commutator superalgebra A(-s) for a simple binary (-1,1) superalgebra A.

Room Temperature Ionic Liquid-Lithium Salt Mixtures: Optical Kerr Effect Dynamical Measurements

The addition of lithium salts to ionic liquids causes an increase in viscosity and a decrease in ionic mobility that hinders their possible application as an alternative solvent in lithium ion batteries. Optically heterodyne-detected optical Kerr effect spectroscopy was used to study the change in dynamics, principally orientational relaxation, caused by the addition of lithium bis(trifluoromethylsulfonyl)imide to the ionic liquid 1-buty1-3-methylimidazolium bis(trifluoromethylsulfonyl)imide. Over the time scales studied (1 ps-16 ns) for the pure ionic liquid, two temperature-independent power laws were observed: the intermediate power law (1 ps to similar to 1 ns), followed by the von Schweidler power law. The von Schweidler power law is followed by the final complete exponential relaxation, which is highly sensitive to temperature. The lithium salt concentration, however, was found to affect both power laws, and a discontinuity could be found in the trend observed for the intermediate power law when the concentration (mole fraction) of lithium salt is close to chi(LiTf(2)N) = 0.2. A mode coupling theory (MCT) schematic model was also used to fit the data for both the pure ionic liquid and the different salt concentration mixtures. It was found that dynamics in both types of liquids are described very well by MCT.

Picosecond Dynamics of Proton Transfer of a 7-Hydroxyflavylium Salt in Aqueous-Organic Solvent Mixtures

The intermediacy of the geminate base proton pair (A*center dot center dot center dot H(+)) in excited-state proton-transfer (ESPT) reactions (two-step mechanism) has been investigated employing the synthetic flavylium salt 7-hydroxy-4-methyl-flavylium chloride (HMF). In aqueous solution, the ESPT mechanism involves solely the excited acid AH* and base A* forms of HMF as indicated by the fluorescence spectra and double-exponential fluorescence decays (two species, two decay times). However, upon addition of either 1,4-dioxane or 1,2-propylene glycol, the decays become triple-exponential with a term consistent with the presence of the geminate base proton pair A*center dot center dot center dot H(+). The geminate pair becomes detectable because of the increase in the recombination rate constant, k(rec), of (A*center dot center dot center dot H(+)) with increasing the mole fraction of added organic cosolvent. Because the two-step ESPT mechanism splits the intrinsic prototropic reaction rates (deprotonation of AH(+)*, k(d), and recombination, k(rec) of A*center dot center dot center dot H(+)) from the diffusion controlled rates (dissociation, k(diss) and formation, k(diff)[H(+)], of A*center dot center dot center dot H+), the experimental detection of the geminate pair provides a wealth of information on the proton-transfer reaction (k(d) and k(rec)) as well as on proton diffusion/migration (k(diss) and k(diff)).

Thermal analysis and compatibility studies of prednicarbate with excipients used in semi solid pharmaceutical form

Differential Scanning Calorimetry (DSC), thermogravimetry/derivative thermogravimetry (TG/DTG) and infrared spectroscopy (IR) techniques were used to investigate the compatibility between prednicarbate and several excipients commonly used in semi solid pharmaceutical form. The thermoanalytical studies of 1:1 (m/m) drug/excipient physical mixtures showed that the beginning of the first thermal decomposition stage of the prednicarbate (T (onset) value) was decreased in the presence of stearyl alcohol and glyceryl stearate compared to the drug alone. For the binary mixture of drug/sodium pirrolidone carboxilate the first thermal decomposition stage was not changed, however the DTG peak temperature (T (peak DTG)) decreased. The comparison of the IR spectra of the drug, the physical mixtures and of the thermally treated samples confirmed the thermal decomposition of prednicarbate. By the comparison of the thermal profiles of 1:1 prednicarbate:excipients mixtures (methylparaben, propylparaben, carbomer 940, acrylate crosspolymer, lactic acid, light liquid paraffin, isopropyl palmitate, myristyl lactate and cetyl alcohol) no interaction was observed.

Thin films of carbohydrate based surfactants and carboxymethylcellulose acetate butyrate mixtures: Morphology and thermal behavior

Thin films of mixtures containing carboxymethylcellulose acetate butyrate (CMCAB) and carbohydrate based surfactant, namely, sorbitan monopalmitate (Span 40) or poly(oxyethylene) sorbitan monopalmitate (Tween 40) were spin-coated onto silicon wafers. The effect of surfactant concentration on resulting film morphology and surface toughness Was Studied by atomic force microscopy (AFM). Upon increasing the concentration of Span 40 in the mixture, films became rougher and more heterogeneous, indicating surface enrichment by Span 40 molecules. In the case of mixtures composed by CMCAB and Tween 40, the increase of Tween 40 in the mixture led to smoother and more homogeneous films, indicating compatibility between both components. Differential scanning calorimetry (DSC) revealed that Span 40 and Tween 40 act as plasticizers for CMCAB, leading to dramatic reduction of glass transition temperature of CMCAB, namely, Delta T(g) = -158 degrees C and Delta T(g)=-179 degrees C. respectively. (C) 2008 Elsevier B.V. All rights reserved.