vol. 10 núm. 2 (2017)

Estimados lectores, en primer lugar, en nombre de todo el equipo de trabajo, queremos enviarles un cordial saludo en estas festividades. Es nuestro deseo que en el 2018 todos sus proyectos profesionales y personales sean exitosos. La revista Comunicaciones en Estad´ıstica continuar´a con su posicionamiento a trav´es de indexaci´on en diferentes bases bibliogr´aficas nacionales e internacionales. Para eso, esperamos seguir contando con el apoyo de todos nuestros autores, revisores y lectores. Estamos abiertos a sus sugerencias y recomendaciones. Antes de empezar con la revisi´on de los art´ıculos de este n´umero quiero agradecer el constante apoyo de las directivas de la Universidad Santo Tom´as que desde hace mas de una d´ecada han apoyado nuestra labor editorial. En particular, quiero agradecer el compromiso de la profesora Hanwen Zhang y del profesor Felipe Ortiz, quien ha acogido con benepl´acito la rigurosa labor de dirigir a la facultad de Estad´ıstica desde la decanatura. Este n´umero de la revista inicia con el trabajo presentado por los profesores Corzo e Hidalgo, quienes consideran el problema de juzgamiento de hip´otesis para el par´ametro de localizaci´on, y proponen estad´ısticas de prueba usando percentiles de la distribuci´on Lambda generalizada como funci´on de puntaje. Por medio de simulaciones, los autores encuentran interesantes propiedades emp´ıricas de las pruebas propuestas en comparaci´on con otras pruebas est´andares.

We propose adaptive rank tests for the location alternative in one sample, using as score function the percentile function of the Generalized Lambda Distribution (GLD ). We give expressions for its eciency as functions of the kurtosis parameters of the distribution used for the score function and those of the sampled distribution. A simulation study shows that the proposed tests maintain its nominal size and that this test using scores functions with small kurtosis parameter, are very ecient for samples coming from distributions with large kurtosis, overtaking the sign test and the Wilcoxon test. Reciprocally, tests which use scores from GLD  distributions with large kurtosis are more ecient when the sample comes from GLD  distributions with small kurtosis.  

Kriging and cokriging and their several related versions are techniques widely known and used in spatial data analysis. However, when the spatial data are functions a bridge between functional data analysis and geostatistics has to be built. I give an overview to cokriging analysis and multivariable spatial prediction to the case where the observations at each sampling location consist of samples of random functions. I extend multivariable geostatistical methods to the functional context. Our cokriging method predicts one variable at a time as in a classical multivariable sense, but considering as auxiliary information curves instead of vectors. I also give an extension of multivariable kriging to the functional context where is defined a predictor of a whole curve based on samples of curves located at a neighborhood of the prediction site. In both cases a non-parametric approach based on basis function expansion is used to estimate the parameters, and I prove that both proposals coincide when using such an approach. A linear model of coregionalization is used to define the spatial dependence among the coefficients of the basis functions, and therefore for estimating the functional parameters. As an illustration the methodological proposals are applied to analyze two real data sets corresponding to average daily temperatures measured at 35 weather stations located in the Canadian Maritime Provinces, and penetration resistance data collected at 32 sampling sites of an experimental plot.

Academic performance is a multicausal phenomenon which clearly shows the learning levels of students. The current research aims to study intelligence as seen by Howard Gardner’s theory, the importance of its multidimensional approach, and its possible applications on the teaching-learning process. It aims to make an exploratory analysis of its representation to describe the main aptitudinal characteristics of freshmen college students. The research is divided into two parts. The first part includes a theoretical analysis, and the second part includes the corresponding empirical study. The study group consists of 156 university students taking a course on Private Law I at the School of Economic Sciences (FCE) of Universidad Nacional del Nordeste (UNNE). This is a descriptive survey design study in which an ad hoc multiple intelligence test was used. It consists of 35 questions organized in 5 items for each considered area (Linguistic, Musical, Logical-Mathematical, Spatial, Bodily-kinesthetic, Intrapersonal and Interpersonal). The empirical stage of this study, the descriptive statistical analysis of reliability and the factorial validity measurement showed that the questionnaire used proved to be a reliable instrument, and that it had construct validity. This tri-factorial model consists of artistic, social and quantitative factors regarding the types of intelligences involved.

We propose a runs test for the hypothesis of symmetry around an unknown median with alternative “stochastically larger than”based on a trimmed runs test for the hypothesis of symmetry around an unknown median with two-tailed alternative proposed in Babativa & Corzo (2010). By a simulation study we show that for samples coming from the Lognormal Distribution, the proposed test maintains the prefixed size and that its empirical power is larger than of the other compared tests proposed in Cabilio & Masaro (1996), Mira (1999) and Miao et al. (2006). 

In basic probability courses, addressing the issue of random vectors shows that the marginal distributions of such vectors can be obtained in a unique way from the joint distribution. The reciprocal of this affirmation does not necessarily have. This article of informative type, tries, by means of a counterexample taken from Embrechts et al. (2002), and that makes use of the theory of copulas, to illustrate the fallacy: “ Marginal distributions and correlation determine the joint distribution ”.Keywords: correlation coefficient; joint distribution; marginal distribution; bivariate normal distribution; copulation theory; random vectors.

Inference in generalized linear mixed models is often based on maximum likelihood theory, which assumes that structures of both fixed effects and random effects is correctly specified. Some authors have shown sensitivity of estimates of fixed effects to random-effects misspecifications. This research aims to identify, using simulation, the impact of misspecifying random-effects distribution in generalized linear mixed models, specifically for the cases of Poisson and Negative Binomial distributions.  

In many situations it is useful to quantify subjective information that one or more experts know about a topic of interest, therefore, an important part of Bayesian statistics is building elicitation methods for finding probability distributions. In order to contribute to the development in this field, a methodology was developed to elicit the parameters of the logistic regression with a single covariate. The proposed method requires to determite the levels of the covarible, at each level a binomial distribution is assumed and the parameter of interest is elicited by using the indirect method hypothetical samples.  

The objective of this work is to implement an elicitation process to estimate the vector of parameters π to multinomial distribution through of Delphi method. Quantification of opinions and beliefs from multiple experts are used to obtain a single distribution that represents the knowledge of all experts that is a different result to get the sum of individual contributions.