Sets of probability distributions, independence, and convexity

This paper analyzes concepts of independence and assumptions of convexity in the theory of sets of probability distributions. The starting point is Kyburg and Pittarelli's discussion of "convex Bayesianism" (in particular their proposals concerning E-admissibility, independence, and convexity). The paper offers an organized review of the literature on independence for sets of probability distributions; new results on graphoid properties and on the justification of "strong independence" (using exchangeability) are presented. Finally, the connection between Kyburg and Pittarelli's results and recent developments on the axiomatization of non-binary preferences, and its impact on "complete" independence, are described.

Levy stable distributions via associated integral transform

We present a method of generation of exact and explicit forms of one-sided, heavy-tailed Levy stable probability distributions g(alpha)(x), 0 <= x < infinity, 0 < alpha < 1. We demonstrate that the knowledge of one such a distribution g a ( x) suffices to obtain exactly g(alpha)p ( x), p = 2, 3, .... Similarly, from known g(alpha)(x) and g(beta)(x), 0 < alpha, beta < 1, we obtain g(alpha beta)( x). The method is based on the construction of the integral operator, called Levy transform, which implements the above operations. For a rational, alpha = l/k with l < k, we reproduce in this manner many of the recently obtained exact results for g(l/k)(x). This approach can be also recast as an application of the Efros theorem for generalized Laplace convolutions. It relies solely on efficient definite integration. (C) 2012 American Institute of Physics. [http://dx.doi.org/10.1063/1.4709443]

Probabilistic patterns of interaction: the effects of link-strength variability on food web structure

Patterns of species interactions affect the dynamics of food webs. An important component of species interactions that is rarely considered with respect to food webs is the strengths of interactions, which may affect both structure and dynamics. In natural systems, these strengths are variable, and can be quantified as probability distributions. We examined how variation in strengths of interactions can be described hierarchically, and how this variation impacts the structure of species interactions in predator-prey networks, both of which are important components of ecological food webs. The stable isotope ratios of predator and prey species may be particularly useful for quantifying this variability, and we show how these data can be used to build probabilistic predator-prey networks. Moreover, the distribution of variation in strengths among interactions can be estimated from a limited number of observations. This distribution informs network structure, especially the key role of dietary specialization, which may be useful for predicting structural properties in systems that are difficult to observe. Finally, using three mammalian predator-prey networks ( two African and one Canadian) quantified from stable isotope data, we show that exclusion of link-strength variability results in biased estimates of nestedness and modularity within food webs, whereas the inclusion of body size constraints only marginally increases the predictive accuracy of the isotope-based network. We find that modularity is the consequence of strong link-strengths in both African systems, while nestedness is not significantly present in any of the three predator-prey networks.

Complexity of inferences in polytree-shaped semi-qualitative probabilistic networks

Semi-qualitative probabilistic networks (SQPNs) merge two important graphical model formalisms: Bayesian networks and qualitative probabilistic networks. They provade a very Complexity of inferences in polytree-shaped semi-qualitative probabilistic networks and qualitative probabilistic networks. They provide a very general modeling framework by allowing the combination of numeric and qualitative assessments over a discrete domain, and can be compactly encoded by exploiting the same factorization of joint probability distributions that are behind the bayesian networks. This paper explores the computational complexity of semi-qualitative probabilistic networks, and takes the polytree-shaped networks as its main target. We show that the inference problem is coNP-Complete for binary polytrees with multiple observed nodes. We also show that interferences can be performed in time linear in the number of nodes if there is a single observed node. Because our proof is construtive, we obtain an efficient linear time algorithm for SQPNs under such assumptions. To the best of our knowledge, this is the first exact polynominal-time algorithm for SQPn. Together these results provide a clear picture of the inferential complexity in polytree-shaped SQPNs.

An Asymmetric Extension for the Family of Elliptical Slash Distributions

In this article, we introduce an asymmetric extension to the univariate slash-elliptical family of distributions studied in Gomez et al. (2007a). This new family results from a scale mixture between the epsilon-skew-symmetric family of distributions and the uniform distribution. A general expression is presented for the density with special cases such as the normal, Cauchy, Student-t, and Pearson type II distributions. Some special properties and moments are also investigated. Results of two real data sets applications are also reported, illustrating the fact that the family introduced can be useful in practice.

Estimation and diagnostics for heteroscedastic nonlinear regression models based on scale mixtures of skew-normal distributions

An extension of some standard likelihood based procedures to heteroscedastic nonlinear regression models under scale mixtures of skew-normal (SMSN) distributions is developed. This novel class of models provides a useful generalization of the heteroscedastic symmetrical nonlinear regression models (Cysneiros et al., 2010), since the random term distributions cover both symmetric as well as asymmetric and heavy-tailed distributions such as skew-t, skew-slash, skew-contaminated normal, among others. A simple EM-type algorithm for iteratively computing maximum likelihood estimates of the parameters is presented and the observed information matrix is derived analytically. In order to examine the performance of the proposed methods, some simulation studies are presented to show the robust aspect of this flexible class against outlying and influential observations and that the maximum likelihood estimates based on the EM-type algorithm do provide good asymptotic properties. Furthermore, local influence measures and the one-step approximations of the estimates in the case-deletion model are obtained. Finally, an illustration of the methodology is given considering a data set previously analyzed under the homoscedastic skew-t nonlinear regression model. (C) 2012 Elsevier B.V. All rights reserved.

Subcritical crack growth and in vitro lifetime prediction of resin composites with different filler distributions

Objectives. Verify the influence of different filler distributions on the subcritical crack growth (SCG) susceptibility, Weibull parameters (m and sigma(0)) and longevity estimated by the strength-probability-time (SPT) diagram of experimental resin composites. Methods. Four composites were prepared, each one containing 59 vol% of glass powder with different filler sizes (d(50) = 0.5; 0.9; 1.2 and 1.9 mu m) and distributions. Granulometric analyses of glass powders were done by a laser diffraction particle size analyzer (Sald-7001, Shimadzu, USA). SCG parameters (n and sigma(f0)) were determined by dynamic fatigue (10(-2) to 10(2) MPa/s) using a biaxial flexural device (12 x 1.2 mm; n = 10). Twenty extra specimens of each composite were tested at 10(0) MPa/s to determine m and sigma(0). Specimens were stored in water at 37 degrees C for 24 h. Fracture surfaces were analyzed under SEM. Results. In general, the composites with broader filler distribution (C0.5 and C1.9) presented better results in terms of SCG susceptibility and longevity. C0.5 and C1.9 presented higher n values (respectively, 31.2 +/- 6.2(a) and 34.7 +/- 7.4(a)). C1.2 (166.42 +/- 0.01(a)) showed the highest and C0.5 (158.40 +/- 0.02(d)) the lowest sigma(f0) value (in MPa). Weibull parameters did not vary significantly (m: 6.6 to 10.6 and sigma(0): 170.6 to 176.4 MPa). Predicted reductions in failure stress (P-f = 5%) for a lifetime of 10 years were approximately 45% for C0.5 and C1.9 and 65% for C0.9 and C1.2. Crack propagation occurred through the polymeric matrix around the fillers and all the fracture surfaces showed brittle fracture features. Significance. Composites with broader granulometric distribution showed higher resistance to SCG and, consequently, higher longevity in vitro. (C) 2012 Academy of Dental Materials. Published by Elsevier Ltd. All rights reserved.

On scale-mixture Birnbaum-Saunders distributions

We present for the first time a justification on the basis of central limit theorems for the family of life distributions generated from scale-mixture of normals. This family was proposed by Balakrishnan et al. (2009) and can be used to accommodate unexpected observations for the usual Birnbaum-Saunders distribution generated from the normal one. The class of scale-mixture of normals includes normal, slash, Student-t, logistic, double-exponential, exponential power and many other distributions. We present a model for the crack extensions where the limiting distribution of total crack extensions is in the class of scale-mixture of normals. (C) 2012 Elsevier B.V. All rights reserved.

The new class of Kummer beta generalized distributions

Ng and Kotz (1995) introduced a distribution that provides greater flexibility to extremes. We define and study a new class of distributions called the Kummer beta generalized family to extend the normal, Weibull, gamma and Gumbel distributions, among several other well-known distributions. Some special models are discussed. The ordinary moments of any distribution in the new family can be expressed as linear functions of probability weighted moments of the baseline distribution. We examine the asymptotic distributions of the extreme values. We derive the density function of the order statistics, mean absolute deviations and entropies. We use maximum likelihood estimation to fit the distributions in the new class and illustrate its potentiality with an application to a real data set.

Generalized beta-generated distributions

This article introduces generalized beta-generated (GBG) distributions. Sub-models include all classical beta-generated, Kumaraswamy-generated and exponentiated distributions. They are maximum entropy distributions under three intuitive conditions, which show that the classical beta generator skewness parameters only control tail entropy and an additional shape parameter is needed to add entropy to the centre of the parent distribution. This parameter controls skewness without necessarily differentiating tail weights. The GBG class also has tractable properties: we present various expansions for moments, generating function and quantiles. The model parameters are estimated by maximum likelihood and the usefulness of the new class is illustrated by means of some real data sets. (c) 2011 Elsevier B.V. All rights reserved.

Likelihood-based inference for power distributions

This paper considers likelihood-based inference for the family of power distributions. Widely applicable results are presented which can be used to conduct inference for all three parameters of the general location-scale extension of the family. More specific results are given for the special case of the power normal model. The analysis of a large data set, formed from density measurements for a certain type of pollen, illustrates the application of the family and the results for likelihood-based inference. Throughout, comparisons are made with analogous results for the direct parametrisation of the skew-normal distribution.