Two-tailed asymptotic inferences for a proportion

This paper evaluates 29 methods for obtaining a two-sided confidence interval for a binomial proportion (16 of which are new proposals) and comes to the conclusion that: Wilson's classic method is only optimal for a confidence of 99%, although generally it can be applied when n≥50; for a confidence of 95% or 90%, the optimal method is the one based on the arcsine transformation (when this is applied to the data incremented by 0.5), which behaves in a very similar manner to Jeffreys’ Bayesian method. A simpler option, though not so good as those just mentioned, is the classic-adjusted Wald method of Agresti and Coull.     

Modeling of Acoustic Signal Energies with a Generalized Frank Copula. A Linguistic Conjecture is Reviewed

In this article a generalized Frank copula was selected to model the dependence between the energy on two frequency bands of the speech signal, coming from eight languages. An algorithm was developed that uses maximum likelihood to choose the best fitting copula’s parameters. Through bootstrap, the algorithm estimates the variability of the parameters for each language and also computes confidence regions by means of Voronoi tesselations. A linguistic conjecture which claims that the languages are organized in three rhythmic classes, was confirmed by the Voronoi regions. Modeling with a uniparametric Frank copula, the different degrees of dependence between the energies were quantified.     

Local influence for functional comparative calibration models with replicated data

We investigate local influence analysis in functional comparative calibration models with replicated data. A method for selecting appropriate perturbation schemes based on the expected Fisher information matrix with respect to the perturbation vector is proposed. It is shown that arbitrarily perturbing these models may result in misleading inference about the influential subjects. First-order influence measures for identifying the correct influential subjects and replicates on corrected score estimators are defined. We introduce different perturbation schemes including perturbation of subjects and replicates on the corrected likelihood function and obtain the density of the perturbed model from which the methodology is based. Particularly, three perturbation of variances schemes could be a better way to handle badly modeled subjects or replicates. Two real data sets are analyzed to illustrate the use of our local influence measures.     

Blocking Probabilities in Erlang Loss Queues with Advance Reservation

We study the blocking probability in a continuous time loss queue, in which resources can be claimed a random time in advance. We identify classes of loss queues where the advance reservation results in increased or decreased blocking probabilities. The lower blocking probabilities are achieved because the system tends to favor short jobs. We provide analytical and numerical results to establish the connection between the system’s parameters and either an increase or decrease of blocking probabilities, compared to the system without reservation.     

On the Evolution and Asymptotic Analysis of Open Markov Populations: Application to Consumption Credit

In this paper, we study, by means of randomized sampling, the long-run stability of some open Markov population fed with time-dependent Poisson inputs. We show that state probabilities within transient states converge—even when the overall expected population dimension increases without bound—under general conditions on the transition matrix and input intensities.

Following the convergence results, we obtain ML estimators for a particular sequence of input intensities, where the sequence of new arrivals is modeled by a sigmoidal function. These estimators allow for the forecast, by confidence intervals, of the evolution of the relative population structure in the transient states.

Applying these results to the study of a consumption credit portfolio, we estimate the implicit default rate.     

Social support and life satisfaction among gay men in Spain

Since the early 1960s, social support has been a topic of interest and study among social psychologists and other professionals investigating social issues. In spite of this growing interest by the scientific community, there are few studies on social support in the lesbian, gay, bisexual, and transgender (LGBT) community, and even fewer on the impact of social support on life satisfaction. In this regard, in Spain, there are very few psychosocial studies on homosexual groups. In the present study, the authors analyze social support data and life satisfaction in a sample of 220 gay residents of Málaga and Sevilla. The results show that friends are the most important source of overall social support, and that, in the family, sisters provide the most support and contribute to increased life satisfaction. On the other hand, social support had an effect on the level of life satisfaction, although the results indicate that factors associated with homosexual identity are the best predictors of life satisfaction. The implications of these results are discussed as well as potential future research.     

Electricity consumption prediction with functional linear regression using spline estimators

A functional linear regression model linking observations of a functional response variable with measurements of an explanatory functional variable is considered. This model serves to analyse a real data set describing electricity consumption in Sardinia. The interest lies in predicting either oncoming weekends’ or oncoming weekdays’ consumption, provided actual weekdays’ consumption is known. A B-spline estimator of the functional parameter is used. Selected computational issues are addressed as well.     

Rivalry and strategic groups: what makes a company a rival?

Strategic group literature has generated a significant amount of research over recent decades. However, the rivalry implications of strategic group have remained unclear. This paper analyses rivalry and strategic groups in the house building industry in a small town from a cognitive approach. We consider rivalry as a subjective and directional phenomenon. Estimating rivalry as the direct identification of competitors we try to explain whether similarity affects rivalry and what factors make a company a “rival”. Results show that perceived rivalry is strongly related to size, past performance, subjective similarity and strategic group structure.