Estimating the number of clusters

Hartigan (1975) defines the number q of clusters in a d ‐variate statistical population as the number of connected components of the set {f > c}, where f denotes the underlying density function on R^d and c is a given constant. Some usual cluster algorithms treat q as an input which must be given in advance. The authors propose a method for estimating this parameter which is based on the computation of the number of connected components of an estimate of {f > c}. This set estimator is constructed as a union of balls with centres at an appropriate subsample which is selected via a nonparametric density estimator of f. The asymptotic behaviour of the proposed method is analyzed. A simulation study and an example with real data are also included.     

Influence diagnostics in the capital asset pricing model under elliptical distributions

In this paper we consider the Capital Asset Pricing Model under Elliptical (symmetric) Distributions. This class of distributions, which contains the normal distribution, t, contaminated normal and power exponential, among others, offers a more flexible framework for modelling asset prices or returns. In order to analyze the sensibility to possible outliers and/or atypical returns of the maximum likelihood estimators, the local influence method was implemented. The results are illustrated by using a set of shares from companies who trade in the Chilean Stock Market. Our main conclusion is that symmetric distributions having heavier tails than those of the normal distribution, especially the t distribution with small degrees of freedom, show a better fit and allow the reduction of the influence of atypical returns in the maximum likelihood estimators.     

Bayesian monitoring of local residual autocorrelations taking into account the run-length

This paper proposes new two-sided monitoring algorithms for detecting the presence of first order residual autocorrelations in Dynamic Normal Models. The methodology uses a Bayesian decision approach with loss function which takes into account the run-length of the process. The power and mean run-length of the proposed algorithms are analysed by Monte Carlo methods. The results obtained improve those corresponding to the monitoring algorithm for residual autocorrelations proposed in Gargallo and Salvador [2003. Monitoring residual autocorrelations in dynamic linear models. Comm. Statist. Simulation Comput. 32(4), 1079–1104.] with respect to the run-length, and also exhibit more homogeneous behaviour.     

Does transformational leadership predict group emotional intelligence in work settings? / ¿Es el liderazgo transformacional un predictor de la inteligencia emocional grupal en los contextos laborales?

Contagion of emotions is a widely accepted characteristic of transformational leaders. However, the impact they may have on the Emotional Intelligence of their subordinates is an open question. In this paper, we analyse whether Transformational Leadership (LTF) perceptions influence the Emotional Intelligence of their groups (GEI). This is a novel approach within the actual interest on emotional intelligence and its role in group results. The participants were 272 subordinates from 52 groups that belonged to different private and public organizations in Spain. They completed a questionnaire including the variables of interest. Our study helps to clarify the relations between TFL perceptions and GEI, showing that TFL and GEI relate at the group level and that TFL is one of the predictors of the perception of GEI in work settings. Thus, the development of emotionally competent transformational leaders will produce emotionally competent groups that might increase their performance, efficiency and other processes (i.e., engagement).     

Reduced Risk-Taking After Prior Losses in Pathological Gamblers Under Treatment and Healthy Control Group but not in Problem Gamblers

A group of pathological gamblers and a group of problem gamblers (i.e., gamblers at risk of becoming pathological) were compared to healthy controls on their risk-taking propensity after prior losses. Each participant played both the Balloon Analogue Risk Taking task (BART) and a modified version of the same task, where individuals face five repeated predetermined early losses at the onset of the game. No significant difference in risk-taking was found between groups on the standard BART task, while significant differences emerged when comparing behaviors in the two tasks: both pathological gamblers and controls reduced their risk-taking tendency after prior losses in the modified BART compared to the standard BART, whereas problem gamblers showed no reduction in risk-taking after prior losses. We interpret these results as a sign of a reduced sensitivity to negative feedback in problem gamblers which might contribute to explain their loss-chasing tendency.     

Qualitative research on homosexual and bisexual behavior relevant to HIV/AIDS

The spread of the international AIDS pandemic has drawn attention to the urgent need for data on human sexual behavior; yet the lack of an established tradition of theory and method in sex research has limited the development of research initiatives in this area. This has been particularly true in the study of homosexual and bisexual behavior, which has relied heavily on the use of quantitative survey methods that largely fail to address cross‐cultural differences in the structure and meaning of same‐sex sexual experience. More qualitative approaches offer the possibility of investigating homosexual and bisexual behavior within a broader social and cultural context and can therefore play an important role in developing a framework for the comparative analysis of behavioral data. This article seeks to contribute to the development of theory and method in sex research by outlining key research issues and possible methodologies for the qualitative investigation of homosexual and bisexual behavior in relation to HIV/AIDS.     

Communicative competence and the facilitating and perturbing factors in the socialisation of immigrant students

This work analyses the communicative competence and the factors that facilitate and perturb the socialisation of immigrant students in primary education. It provides greater knowledge concerning the relationship between the immigrant student's social and linguistic competence. It also analyses the presence of difficulties in the different language components (morphology, syntax, semantics and pragmatics). The sample is made up of a total of 326 immigrant students between 6 and 12 years of age, attending 10 different schools. The study demonstrates that immigrant students possess a low level of linguistic dominion. All the linguistic components analysed are affected, although greater difficulties are evident in morphology and syntax than in semantics and pragmatics. The relationship between linguistic competence and the factors that facilitate and perturb socialisation is underlined. This work concludes that there is a significant relation between semantics and pragmatics and several socialisation factors (leadership, aggressiveness–stubbornness and anxiety–shyness). The educational centres should be aware of the complicated learning process that immigrant students have to go through.