A comparison of classification models to identify the Fragile X Syndrome

The main models of machine learning are briefly reviewed and considered for building a classifier to identify the Fragile X Syndrome (FXS). We have analyzed 172 patients potentially affected by FXS in Andalusia (Spain) and, by means of a DNA test, each member of the data set is known to belong to one of two classes: affected, not affected. The whole predictor set, formed by 40 variables, and a reduced set with only nine predictors significantly associated with the response are considered. Four alternative base classification models have been investigated: logistic regression, classification trees, multilayer perceptron and support vector machines. For both predictor sets, the best accuracy, considering both the mean and the standard deviation of the test error rate, is achieved by the support vector machines, confirming the increasing importance of this learning algorithm. Three ensemble methods - bagging, random forests and boosting - were also considered, amongst which the bagged versions of support vector machines stand out, especially when they are constructed with the reduced set of predictor variables. The analysis of the sensitivity, the specificity and the area under the ROC curve agrees with the main conclusions extracted from the accuracy results. All of these models can be fitted by free R programs.     

`Sex-Equal' Stable Matchings

The paper defines a measure on the set of stable matchings in the marriage problem. This measure is based on the minimization of the envy difference between the sets of men and women, while preserving stability and selects stable matchings with the least conflict of interest between both groups of agents. The solution concept proposed is called Sex-equal Matching (SEM) and the paper also provides an algorithm to compute the set of SEM.     

On cumulative entropies

In analogy with the cumulative residual entropy recently proposed by Wang et al. [2003a. A new and robust information theoretic measure and its application to image alignment. In: Information Processing in Medical Imaging. Lecture Notes in Computer Science, vol. 2732, Springer, Heidelberg, pp. 388–400; 2003b. Cumulative residual entropy, a new measure of information and its application to image alignment. In: Proceedings on the Ninth IEEE International Conference on Computer Vision (ICCV’03), vol. 1, IEEE Computer Society Press, Silver Spring, MD, pp. 548–553], we introduce and study the cumulative entropy, which is a new measure of information alternative to the classical differential entropy. We show that the cumulative entropy of a random lifetime X can be expressed as the expectation of its mean inactivity time evaluated at X. Hence, our measure is particularly suitable to describe the information in problems related to ageing properties of reliability theory based on the past and on the inactivity times. Our results include various bounds to the cumulative entropy, its connection to the proportional reversed hazards model, and the study of its dynamic version that is shown to be increasing if the mean inactivity time is increasing. The empirical cumulative entropy is finally proposed to estimate the new information measure.     

Educational responses to immigrant students in Madrid

During the last few years, changes in the Spanish educational system have had a far reaching impact. Several factors have been critical: (1) the progressive decentralization of education by the government, now a responsibility of regional governments; (2) the extension of compulsory education to the age of 16; and finally (3) the increase in the number of immigrant students, which has significantly added to the existing cultural diversity. The enrolment of immigrant students in Spanish schools is a relatively recent phenomenon (starting 15 years ago) when compared with other European countries. Madrid is the region in Spain with the largest number of students. As most of these students were born outside of Spain, we cannot yet speak of a second generation. The research described here investigated how the educational system in Madrid confronted the challenge of an increasing number of immigrant students. The institutional response was the Madrid Regional Government’s Compensatory Education Regional Plan. This encompasses several measures, which are described here. After a critical analysis of educational policies pertaining to immigrant pupils, the paper suggests ways of overcoming a purely compensatory approach. Intercultural education plays a key role is such considerations.     

Hurricane Katrina's Impact on African Americans' and European Americans' Endorsement of the Protestant Work Ethic

The Protestant work ethic (PWE), the belief that hard work leads to success, is a quintessentially American belief. The present research addresses a critical gap in psychological research on PWE: can a single, large-scale sociopolitical event (government's response to Hurricane Katrina) produce changes in PWE? We review evidence showing that the salience of Katrina led to a reduction in African Americans' (not European Americans') endorsement of PWE and that this result appears explained by African Americans' greater belief in the government's inadequate response to Katrina victims, who were predominately African American. The implications of differential endorsement of PWE for future expectations of societal treatment, motivation to pursue important goals, and willingness to endorse structural corrections of inequality are discussed.     

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.     

Voting in professional associations: The case of the American sociological association revisited

Who votes in ASA elections? This article examines data on voter turnout from two recent presidential contests of the American Sociological Association in an analysis of the determinants of election participation. Extending the 1981 Ridgeway and Moore study of voting dynamics in the ASA, we hypothesize that intraorganizational networks and particular demongraphic characteristics link ASA members to the discipline in a manner analogous to the way such factors operate in the national electorate. On the basis of data compiled from 1985 and 1986 ASA election returns, we find that network factors are the most salient determinants of voting behavior. We conclude that those organizational ties that effectively link members, however directly or indirectly, to the larger Association are the most predictive of propensity to vote.     

Flexible models for non-equidispersed count data: comparative performance of parametric models to deal with underdispersion

AStA Advances in Statistical Analysis - Count data as response variables are commonly modeled using Poisson regression models, which require equidispersion, i.e., equal mean and variance. However,...