Robust estimators for additive models using backfitting

Additive models provide an attractive setup to estimate regression functions in a nonparametric context. They provide a flexible and interpretable model, where each regression function depends only on a single explanatory variable and can be estimated at an optimal univariate rate. Most estimation procedures for these models are highly sensitive to the presence of even a small proportion of outliers in the data. In this paper, we show that a relatively simple robust version of the backfitting algorithm (consisting of using robust local polynomial smoothers) corresponds to the solution of a well-defined optimisation problem. This formulation allows us to find mild conditions to show Fisher consistency and to study the convergence of the algorithm. Our numerical experiments show that the resulting estimators have good robustness and efficiency properties. We illustrate the use of these estimators on a real data set where the robust fit reveals the presence of influential outliers.     

Empirical phi-divergence test statistics for the difference of means of two populations

Empirical phi-divergence test statistics have demostrated to be a useful technique for the simple null hypothesis to improve the finite sample behavior of the classical likelihood ratio test statistic, as well as for model misspecification problems, in both cases for the one population problem. This paper introduces this methodology for two-sample problems. A simulation study illustrates situations in which the new test statistics become a competitive tool with respect to the classical z test and the likelihood ratio test statistic.     

Beyond convergence: unveiling variations of external franchise in Latin America and the Caribbean from 1950 to 2015

A growing literature deals with the models that states have developed to reach out to their emigrant communities. The literature covers a wide range of initiatives, most notably electoral policies. In this line of research, we present a comparative view of the citizenship policies of Latin American and Caribbean states using a data set that includes information (yearly observations from 1950 to 2015) of the external franchise policies of 22 countries. First, this paper describes the scope of inclusion of non-resident citizens in terms of electoral rights. Second, we study the evolution over time of the external franchise policies of the countries under study. Despite cultural, historical and obvious geographic commonalities across countries, the analyses reveal that the convergence trend in the external franchise policies developed by Latin American and Caribbean countries is limited to a most general level. Below that level many variations in terms of specific electoral rights, types and venues of representation of emigrants are observable. These variations range from exclusion of non-resident citizens in terms of electoral rights, to full inclusion, when emigrants have active and passive electoral rights in all the national elections held in the states of origin (presidential and/or legislative).     

Relationship between the degree of perineal trauma at vaginal birth and change in haemoglobin concentration

Background

Postpartum anaemia is a problem with high prevalence that significantly affects maternal recovery. Among the causal factors is perineal trauma. However, it is still not known what degree of perineal trauma produces a greater reduction of haemoglobin.

Experiences of Violence Among Transgender Women in Puerto Rico: An Underestimated Problem

Violence is a public health concern faced on a daily basis by transgender women. Literature has documented how it adversely affects quality of life and health and in some instances leads to homicide. Considering the lack of research documenting the experiences of violence among transgender women, the objective of this article was to explore manifestations of violence among this population in Puerto Rico. The data presented in this article are part of a larger study on transgender/transsexual health in Puerto Rico. For the purpose of this article we focus on the quantitative data analysis. Participants (N = 59 transgender women) were recruited via respondent driven sampling. Implications and specific recommendations are discussed in light of these findings.     

Harassment Patterns and Risk Profile in Spanish Trans Persons

This article describes the harassment patterns and the risk profile in trans people living in Spain. A sample of 212 trans persons, aged 10–62, participated in this cross-sectional study. Results showed a high percentage of harassment (59.9%) and frequency of daily harassment (12.6%), especially verbal attacks (59%) that occurred in public spaces (49.1%) and within educational contexts (46.2%). Harassment is more prevalent in trans women than men. Those who disclose their gender identities at a younger age experience higher percentages and frequency of harassment than those who disclose at an older age. They also suffer more harassment of different types. The risk profile of harassment indicates that older trans women are more likely to suffer harassment than younger ones, and the risk decreases each year they delay their gender identity disclosure. The elimination of transphobic attitudes and the promotion of gender justice should be priority strategies in Spain.     

Improving the biomarker diagnostic capacity via functional transformations

The use of the area under the receiver-operating characteristic, ROC, curve (AUC) as an index of diagnostic accuracy is overwhelming in fields such as biomedical science and machine learning. It seems that a larger AUC value has become synonymous with a better performance. The functional transformation of the marker values has been proposed in the specialized literature as a procedure for increasing the AUC and therefore the diagnostic accuracy. However, the classification process is based on some regions (classification subsets) which support the decision made; one subject is classified as positive if its marker is within this region and classified as negative otherwise. In this paper we study the capacity of improving the classification performance of univariate biomarkers via functional transformations and the impact of this transformation on the final classification regions based on a real-world dataset. Particularly, we consider the problem of determining the gender of a subject based on the Mode frequency of his/her voice. The shape of the cumulative distribution function of this characteristic in both the male and the female groups makes the resulting classification problem useful for illustrating the differences between having useful diagnostic rules and obtaining an optimal AUC value. Our point is that improving the AUC by means of a functional transformation can produce classification regions with no practical interpretability. We propose to improve the classification accuracy by making the selection of the classification subsets more flexible while preserving their interpretability. Besides, we provide different graphical approximations which allow us a better understanding of the classification problem.     

Family Policy Index: A Tool for Policy Makers to Increase the Effectiveness of Family Policies

Social Indicators Research - This paper presents the Family Policy Index (XFPI), an analytical tool designed to measure and compare different models of countries’ provision of educational...     

Evaluation of the location of cities in terms of land cover on the example of Poland

Urban Ecosystems - The increasing availability of remote sensing materials of varying spatial resolution inclines to look for methods enabling their use, both at planning the spatial structure of...     

Factorial Validity of the Maslach Burnout Inventory-Human Services Survey (MBI-HSS) in a Sample of Spanish Social Workers

Burnout has been considered important to understanding the well-being of social workers and the quality of the services they render. Despite the ample international usage of the Maslach Burnout Inventory, its psychometric properties have come into question and alternative models of measuring the inventory have been suggested. The purpose of this study was to examine the psychometric properties and the applicability of a Spanish version of the Maslach Burnout Inventory-Human Services Survey (MBI-HSS) in an incidental sample of 947 social workers. Three alternative models of the MBI-HSS were tested for the purpose of identifying the most suitable model for measuring burnout in Spain. The confirmatory factor analysis supported the theory that the model of three correlated factors was superior to alternative models of one and two factors. The structure of three factors (emotional exhaustion, depersonalization, and personal accomplishment) and 19 items showed the best adjustment and a suitable internal consistency of the dimensions of the MBI-HSS. These findings demonstrate that the MBI-HSS has validity and reliability acceptable for measuring burnout in social workers, providing valuable information to the managers of social services in order to reduce burnout among social workers. The limitations of the study and recommendations for future investigation are emphasized.