Wave-height hazard analysis in Eastern Coast of Spain : Bayesian approach using generalized Pareto distribution

Standard practice of wave-height hazard analysis often pays little attention to the uncertainty of assessed return periods and occurrence probabilities. This fact favors the opinion that, when large events happen, the hazard assessment should change accordingly. However, uncertainty of the hazard estimates is normally able to hide the effect of those large events. This is illustrated using data from the Mediterranean coast of Spain, where the last years have been extremely disastrous. Thus, it is possible to compare the hazard assessment based on data previous to those years with the analysis including them. With our approach, no significant change is detected when the statistical uncertainty is taken into account. The hazard analysis is carried out with a standard model. Time-occurrence of events is assumed Poisson distributed. The wave-height of each event is modelled as a random variable which upper tail follows a Generalized Pareto Distribution (GPD). Moreover, wave-heights are assumed independent from event to event and also independent of their occurrence in time. A threshold for excesses is assessed empirically. The other three parameters (Poisson rate, shape and scale parameters of GPD) are jointly estimated using Bayes' theorem. Prior distribution accounts for physical features of ocean waves in the Mediterranean sea and experience with these phenomena. Posterior distribution of the parameters allows to obtain posterior distributions of other derived parameters like occurrence probabilities and return periods. Predictives are also available. Computations are carried out using the program BGPE v2.0

Bayes linear spaces

Linear spaces consisting of σ-finite probability measures and infinite measures (improper priors and likelihood functions) are defined. The commutative group operation, called perturbation, is the updating given by Bayes theorem; the inverse operation is the Radon-Nikodym derivative. Bayes spaces of measures are sets of classes of proportional measures. In this framework, basic notions of mathematical statistics get a simple algebraic interpretation. For example, exponential families appear as affine subspaces with their sufficient statistics as a basis. Bayesian statistics, in particular some well-known properties of conjugated priors and likelihood functions, are revisited and slightly extended

Validation des SCORES cliniques: notions théoriques et pratiques de base. [Validation of clinical scores: theoretical and practical basic notions].

Chaque jour, le médecin utilise dans sa pratique des scores cliniques. Ces scores sont souvent des aides à la décision médicale. Les étapes de validation des scores cliniques sont par contre souvent méconnues du médecin. Cette revue rappelle les bases théoriques de la validation d'un score clinique et propose des exercices pratiques. [Abstract] Physicians are using clinical scores on a regular basis. These scores are generally helpful in making medical decisions. However, the process of validation of clinical scores is often unknown to the physicians. This paper reviews the theory of validation of clinical scores and proposes practical exercises.

Consistency and the core of multi-sided assignment markets

[cat] En aquest treball es demostra que en el domini dels jocs d’assignació equilibrats multisectorials (Quint, 1991), el core és l’única solució no buida que satisfà derived consistency i projection consistency. També es caracteritza el core en tota la classe dels jocs d’assignació multisectorials amb els axiomes de singleness best, individual antimonotonicity i derived consistency. Com a casos particulars, s’obtenen dues noves axiomàtiques del core per als jocs d’assignació bilaterals (Shapley and Shubik, 1972).

The Banzhaf Value in the Presence of Externalities

[eng] We propose two generalizations of the Banzhaf value for partition function form games. In both cases, our approach is based on probability distributions over the set of possible coalition structures that may arise for any given set of agents. First, we introduce a family of values, one for each collection of the latter probability distributions, defined as the Banzhaf value of an expected coalitional game. Then, we provide two characterization results for this new family of values within the framework of all partition function games. Both results rely on a property of neutrality with respect to amalgamation of players. Second, as this collusion transformation fails to be meaningful for simple games in partition function form, we propose another generalization of the Banzhaf value which also builds on probability distributions of the above type. This latter family is characterized by means of a neutrality property which uses an amalgamation transformation of players for which simple games are closed.

Consistency and the core of multi-sided assignment markets

[cat] En aquest treball es demostra que en el domini dels jocs d’assignació equilibrats multisectorials (Quint, 1991), el core és l’única solució no buida que satisfà derived consistency i projection consistency. També es caracteritza el core en tota la classe dels jocs d’assignació multisectorials amb els axiomes de singleness best, individual antimonotonicity i derived consistency. Com a casos particulars, s’obtenen dues noves axiomàtiques del core per als jocs d’assignació bilaterals (Shapley and Shubik, 1972).

The Banzhaf Value in the Presence of Externalities

[eng] We propose two generalizations of the Banzhaf value for partition function form games. In both cases, our approach is based on probability distributions over the set of possible coalition structures that may arise for any given set of agents. First, we introduce a family of values, one for each collection of the latter probability distributions, defined as the Banzhaf value of an expected coalitional game. Then, we provide two characterization results for this new family of values within the framework of all partition function games. Both results rely on a property of neutrality with respect to amalgamation of players. Second, as this collusion transformation fails to be meaningful for simple games in partition function form, we propose another generalization of the Banzhaf value which also builds on probability distributions of the above type. This latter family is characterized by means of a neutrality property which uses an amalgamation transformation of players for which simple games are closed.

Indicators for the characterization of discrete Choquet integrals

Ordered weighted averaging (OWA) operators and their extensions are powerful tools used in numerous decision-making problems. This class of operator belongs to a more general family of aggregation operators, understood as discrete Choquet integrals. Aggregation operators are usually characterized by indicators. In this article four indicators usually associated with the OWA operator are extended to discrete Choquet integrals: namely, the degree of balance, the divergence, the variance indicator and Renyi entropies. All of these indicators are considered from a local and a global perspective. Linearity of indicators for linear combinations of capacities is investigated and, to illustrate the application of results, indicators of the probabilistic ordered weighted averaging -POWA- operator are derived. Finally, an example is provided to show the application to a specific context.

The connection between distortion risk measures and ordered weighted averaging operators

Distortion risk measures summarize the risk of a loss distribution by means of a single value. In fuzzy systems, the Ordered Weighted Averaging (OWA) and Weighted Ordered Weighted Averaging (WOWA) operators are used to aggregate a large number of fuzzy rules into a single value. We show that these concepts can be derived from the Choquet integral, and then the mathematical relationship between distortion risk measures and the OWA and WOWA operators for discrete and finite random variables is presented. This connection offers a new interpretation of distortion risk measures and, in particular, Value-at-Risk and Tail Value-at-Risk can be understood from an aggregation operator perspective. The theoretical results are illustrated in an example and the degree of orness concept is discussed.

A Sparse Bayesian Approach for Joint Feature Selection and Classifier Learning

Peer-reviewed

Cómo aplicar árboles de decisión en SPSS

Un árbol de decisión es una forma gráfica y analítica de representar todos los eventos (sucesos) que pueden surgir a partir de una decisión asumida en cierto momento. Nos ayudan a tomar la decisión más"acertada", desde un punto de vista probabilístico, ante un abanico de posibles decisiones. Estos árboles permiten examinar los resultados y determinar visualmente cómo fluye el modelo. Los resultados visuales ayudan a buscar subgrupos específicos y relaciones que tal vez no encontraríamos con estadísticos más tradicionales. Los árboles de decisión son una técnica estadística para la segmentación, la estratificación, la predicción, la reducción de datos y el filtrado de variables, la identificación de interacciones, la fusión de categorías y la discretización de variables continuas. La función árboles de decisión (Tree) en SPSS crea árboles de clasificación y de decisión para identificar grupos, descubrir las relaciones entre grupos y predecir eventos futuros. Existen diferentes tipos de árbol: CHAID, CHAID exhaustivo, CRT y QUEST, según el que mejor se ajuste a nuestros datos.

Social differences in avoidable mortality between small areas of 15 European cities: an ecological study

Health and inequalities in health among inhabitants of European cities are of major importance for European public health and there is great interest in how different health care systems in Europe perform in the reduction of health inequalities. However, evidence on the spatial distribution of cause-specific mortality across neighbourhoods of European cities is scarce. This study presents maps of avoidable mortality in European cities and analyses differences in avoidable mortality between neighbourhoods with different levels of deprivation. Methods: We determined the level of mortality from 14 avoidable causes of death for each neighbourhood of 15 large cities in different European regions. To address the problems associated with Standardised Mortality Ratios for small areas we smooth them using the Bayesian model proposed by Besag, York and Mollié. Ecological regression analysis was used to assess the association between social deprivation and mortality. Results: Mortality from avoidable causes of death is higher in deprived neighbourhoods and mortality rate ratios between areas with different levels of deprivation differ between gender and cities. In most cases rate ratios are lower among women. While Eastern and Southern European cities show higher levels of avoidable mortality, the association of mortality with social deprivation tends to be higher in Northern and lower in Southern Europe. Conclusions: There are marked differences in the level of avoidable mortality between neighbourhoods of European cities and the level of avoidable mortality is associated with social deprivation. There is no systematic difference in the magnitude of this association between European cities or regions. Spatial patterns of avoidable mortality across small city areas can point to possible local problems and specific strategies to reduce health inequality which is important for the development of urban areas and the well-being of their inhabitants

Cancer mortality inequalities in urban areas: a Bayesian small area analysis in Spanish cities [correcció]

After publication of this work in 'International Journal of Health Geographics' on 13 january 2011 was wrong. The map of Barcelona in Figure two (figure 1 here) was reversed. The final correct Figure is presented here

Cancer mortality inequalities in urban areas: a Bayesian small area analysis in Spanish cities

Intra-urban inequalities in mortality have been infrequently analysed in European contexts. The aim of the present study was to analyse patterns of cancer mortality and their relationship with socioeconomic deprivation in small areas in 11 Spanish cities

Applications of Industrial Statistics

This dissertation examines knowledge and industrial knowledge creation processes. It looks at the way knowledge is created in industrial processes based on data, which is transformed into information and finally into knowledge. In the context of this dissertation the main tool for industrial knowledge creation are different statistical methods. This dissertation strives to define industrial statistics. This is done using an expert opinion survey, which was sent to a number of industrial statisticians. The survey was conducted to create a definition for this field of applied statistics and to demonstrate the wide applicability of statistical methods to industrial problems. In this part of the dissertation, traditional methods of industrial statistics are introduced. As industrial statistics are the main tool for knowledge creation, the basics of statistical decision making and statistical modeling are also included. The widely known Data Information Knowledge Wisdom (DIKW) hierarchy serves as a theoretical background for this dissertation. The way that data is transformed into information, information into knowledge and knowledge finally into wisdom is used as a theoretical frame of reference. Some scholars have, however, criticized the DIKW model. Based on these different perceptions of the knowledge creation process, a new knowledge creation process, based on statistical methods is proposed. In the context of this dissertation, the data is a source of knowledge in industrial processes. Because of this, the mathematical categorization of data into continuous and discrete types is explained. Different methods for gathering data from processes are clarified as well. There are two methods for data gathering in this dissertation: survey methods and measurements. The enclosed publications provide an example of the wide applicability of statistical methods in industry. In these publications data is gathered using surveys and measurements. Enclosed publications have been chosen so that in each publication, different statistical methods are employed in analyzing of data. There are some similarities between the analysis methods used in the publications, but mainly different methods are used. Based on this dissertation the use of statistical methods for industrial knowledge creation is strongly recommended. With statistical methods it is possible to handle large datasets and different types of statistical analysis results can easily be transformed into knowledge.