Bayesian Methodology for Model Uncertainty Using Model Performance Data

A simple and useful characterization of many predictive models is in terms of model structure and model parameters. Accordingly, uncertainties in model predictions arise from uncertainties in the values assumed by the model parameters (parameter uncertainty) and the uncertainties and errors associated with the structure of the model (model uncertainty). When assessing uncertainty one is interested in identifying, at some level of confidence, the range of possible and then probable values of the unknown of interest. All sources of uncertainty and variability need to be considered. Although parameter uncertainty assessment has been extensively discussed in the literature, model uncertainty is a relatively new topic of discussion by the scientific community, despite being often the major contributor to the overall uncertainty. This article describes a Bayesian methodology for the assessment of model uncertainties, where models are treated as sources of information on the unknown of interest. The general framework is then specialized for the case where models provide point estimates about a single‐valued unknown, and where information about models are available in form of homogeneous and nonhomogeneous performance data (pairs of experimental observations and model predictions). Several example applications for physical models used in fire risk analysis are also provided.     

A Bayesian model for multinomial sampling with misclassified data

In this paper the issue of making inferences with misclassified data from a noisy multinomial process is addressed. A Bayesian model for making inferences about the proportions and the noise parameters is developed. The problem is reformulated in a more tractable form by introducing auxiliary or latent random vectors. This allows for an easy-to-implement Gibbs sampling-based algorithm to generate samples from the distributions of interest. An illustrative example related to elections is also presented.     

Bayesian assessment of times to diagnosis in breast cancer screening

Breast cancer is one of the diseases with the most profound impact on health in developed countries and mammography is the most popular method for detecting breast cancer at a very early stage. This paper focuses on the waiting period from a positive mammogram until a confirmatory diagnosis is carried out in hospital. Generalized linear mixed models are used to perform the statistical analysis, always within the Bayesian reasoning. Markov chain Monte Carlo algorithms are applied for estimation by simulating the posterior distribution of the parameters and hyperparameters of the model through the free software WinBUGS.     

Infants’ Style of Emotion Regulation with Their Mothers and Fathers: Concordance between Parents and the Contribution of Father–Infant Interaction Quality

The concordance between infants’ emotion regulation styles with different partners has not been consistently analysed nor have the relational correlates of such potential across‐partners similarities. We explored these issues by assessing 10‐month‐olds’ (59.6 percent boys) emotion regulation styles separately with mother and father and by evaluating mother–infant and father–infant interaction quality. The sample consisted of 50 low‐risk families. Two home visits were conducted and similar procedures were adopted for each visit. Parent–infant interaction quality was assessed during daily routines and during free play; both parents independently completed a temperament questionnaire. Infant emotion regulation was assessed in a semi‐structured problem‐solving task: adaptive vs. maladaptive (under and over‐regulation) styles. As predicted, infants’ emotion regulation with their mothers and fathers were related. However, only father–infant interaction quality predicted infants’ emotion regulation concordance: lower interaction quality was associated with maladaptive concordance compared with non‐concordance and higher interaction quality was associated with adaptive concordance compared with non‐concordance. Our results support the claim that by the end of the first year of life, infants use similar emotion regulation styles with mother and father and point to father–infant interaction as an important correlate of emotion regulation across‐parents.     

Order statistics from overlapping samples: bivariate densities and regression properties

In this paper, we are interested in the joint distribution of two order statistics from overlapping samples. We give an explicit formula for the distribution of such a pair of random variables under the assumption that the parent distribution is absolutely continuous. We are also interested in the question to what extent conditional expectation of one of such order statistic given another determines the parent distribution. In particular, we provide a new characterization by linearity of regression of an order statistic from the extended sample given the one from the original sample, special case of which solves a problem explicitly stated in the literature. It appears that to describe the correct parent distribution it is convenient to use quantile density functions. In several other cases of regressions of order statistics we provide new results regarding uniqueness of the distribution in the sample.     

A maximal domain of preferences for strategy-proof,efficient, and simple rules in the division problem

The division problem consists of allocating an amount M of a perfectly divisible good among a group of n agents. Sprumont (1991) showed that if agents have single-peaked preferences over their shares, the uniform rule is the unique strategy-proof, efficient, and anonymous rule. Ching and Serizawa (1998) extended this result by showing that the set of single-plateaued preferences is the largest domain, for all possible values of M, admitting a rule (the extended uniform rule) satisfying strategy-proofness, efficiency and symmetry. We identify, for each M and n, a maximal domain of preferences under which the extended uniform rule also satisfies the properties of strategy-proofness, efficiency, tops-onlyness, and continuity. These domains (called partially single-plateaued) are strictly larger than the set of single-plateaued preferences. However, their intersection, when M varies from zero to infinity, coincides with the set of single-plateaued preferences.An earlier version of this paper circulated under the title A maximal domain of preferences for tops-only rules in the division problem. We are grateful to an associate editor of this journal for comments that helped to improve the presentation of the paper and to Matt Jackson for suggesting us the interest of identifying a maximal domain of preferences for tops-only rules. We are also grateful to Dolors Berga, Flip Klijn, Howard Petith, and a referee for helpful comments. The work of Alejandro Neme is partially supported by Research Grant 319502 from the Universidad Nacional de San Luis. The work of Jordi Massó is partially supported by Research Grants BEC2002-02130 from the Spanish Ministerio de Ciencia y Tecnología and 2001SGR-00162 from the Generalitat de Catalunya, and by the Barcelona Economics Program of CREA from the Generalitat de Catalunya. The paper was partially written while Alejandro Neme was visiting the UAB unde r a sabbatical fellowship from the Generalitat de Catalunya.     

Sexual behavior among HIV-positive men who have sex with men: what's in a label?

Relatively little attention has been paid to the use and importance of labels used by men who have sex with men to describe insertive or receptive sexual behavior during intercourse. This study examines sexual self-labels, sexual behavior, HIV transmission risk, and psychological functioning among 205 HIV-seropositive men who have sex with men. The majority of participants (88%) identified as a top, a bottom, or versatile. Tops were more likely to engage in insertive anal intercourse than bottoms, and bottoms were more likely to engage in receptive anal intercourse than tops, with versatiles reporting intermediate rates of both behaviors. Although the results suggest preliminary evidence regarding the predictive utility of self-labels, sexual behaviors of self-label groups were greatly overlapping. Differences were found among self-label groups in gay self-identification, internalized homophobia, sexual sensation seeking, and anxiety. Results suggest an added value in assessing self-labels in addition to asking about sexual behavior.     

Implementation of Intercultural Education Programmes based on Cooperative Learning

An intercultural programme must not overlook the elimination of racist attitudes, but should especially promote multicultural and democratic values.

In Spain, one of the most rejected groups is Gypsy people and their schooling is a problematic issue. We believe that intercultural attitude training programmes can be a practical pedagogical answer for promoting acceptance and respect for diversity.

To do this, we have chosen educational strategies of Cooperation in the Classroom, Active Participation and Persuasive Communication. All of them involve a search for new perspectives, the use of sociocognitive conflict as a driving impulse for learning, and an atmosphere of equality, respect and participation in the classroom.

We present in this paper one of the school programmes we have implemented in Valencia. This programme has been designed to be integrated within the ordinary school curriculum and not regarded as an added out‐of‐school activity. In order to implement it, we organised a teacher‐training course to analyse the intercultural model, to show the need for attitude training in education and to offer pedagogical guidance for the implementation of this type of intercultural programme.

The results of the programme show the improvement in pupils ‘ attitudes towards Gypsy people and cultural diversity in general.     

Income and Happiness in Time of Post-Communist Modernization

This paper discusses the relations between economic development, family income, and happiness in post-communist Poland from the point of view of Inglehart’s theory of modernization. The happiness is understood as satisfaction with income and life, and as psychological well-being. The analysis of survey data yields the conclusion that economic development reduces the strength of the relations between income and satisfaction as well as between income and psychological well-being. These findings may be explained by changes in the value system from collectivist/materialist to individualist/post-materialist, even when these values are not directly measured. The analyzed data are from a series of representative surveys conducted in Poland during a period of political and economic transformation (i.e., between 1989 and 2008). Official statistical data on Polish economic development during the same period are used as a background for survey results. The relations between income and happiness change in Poland in a way consistent with Inglehart’s modernization theory.