Nonparametric estimation of the ROC curve based on smoothed empirical distribution functions

The receiver operating characteristic (ROC) curve is a graphical representation of the relationship between false positive and true positive rates. It is a widely used statistical tool for describing the accuracy of a diagnostic test. In this paper we propose a new nonparametric ROC curve estimator based on the smoothed empirical distribution functions. We prove its strong consistency and perform a simulation study to compare it with some other popular nonparametric estimators of the ROC curve. We also apply the proposed method to a real data set.     

The International Mobility of Highly Skilled Workers in Transnational Corporations: The Macro and Micro Factors of the Organizational Migration of Cadres1

The worldwide movement of highly skilled workers (cadres) in transnational corporations has long been known to literature in the field, yet has not been thoroughly researched. The mechanisms governing their international circulation are, in themselves, somewhat specific. The fact that they use an organizational “channel” for migration means that the constraints differ from those that act on “independent” economic migrants with either low or high levels of skill (the so‐called brain drain). This article focuses on some of the manifestations of this mobility. Its dependence on a set of variables can be considerable: the firm's development phase, investment target choice, leading activity (manufacturing or services), form of technology, type of firm (using greenfield or brownfield investment), whether a firm acquired is healthy or undergoing an economic crisis, and nationality or corporate culture. The occupational insertion of cadres leads to further constraints: while the strictly “technical” assignments generally stem from skill shortages, the general “management” appointments mainly result from questions arising from control and trust. As a whole, the flows of highly skilled workers seem to be related to multiple variables – either social, organizational or individual – which make it difficult to predict future trends.     

How race affects dismissals of college football coaches

We employ a discretetime hazard model and a Blinder-decomposition approach to explore the possibility of racial discrimination in the dismissal and retention of college football coaches by university administrations. A rich data set consisting of 81 institutions over an 11-year period (1990–2000) that contains, in addition to a coach's race, variables on cumulative winning records, annual on-the-field improvements, and pre-/post-season game participation by institutions and their coaches is employed. Our study finds that black coaches, on average, face a dismissal probability that is 9.6 percentage points below that of their nonblack counterparts, ceteris paribus, suggesting that black head coaches may be the beneficiaries of favorable treatment by university administrators. Such a result likely stems from universities ' approach to social concerns involving race and gender issues. This finding also fits a construct that considers workplace discrimination as multi-dimensional. For example, black representation in the college football coaching ranks may be disproportionately low, possibly as a result of discrimination. However, once hired, black coaches are given more time to succeed than nonblacks, other things constant.     

“Good” corporate governance and the quality of internal auditing departments in Italian listed firms. An exploratory investigation in Italian listed firms

One of the most important issue relating to corporate governance reports refers to their ability to provide users with a complete set of information regarding the effective ability of an entity to achieve oversight objectives by the compliance to corporate governance practices required by a specific law or industry code. In addition, other features, such as the quality of the internal auditing function or the sensitivity of top management to issues relating to corporate internal controls and risk management, can also be taken into account when formulating a judgment on the quality of corporate governance practices. Is there an association between the compliance to codes and internal controls effectiveness? We propose to assess the quality of corporate governance through a proxy that considers several characteristics of internal audit departments and combines them to determine an Internal Audit Departments global quality index—IAD Index. To define IAD global quality we consider the effectiveness of an internal audit function analysing its operational aspects. The IAD Index is based on several signalling elements that previous literature assumed as proxies for quality of IADs which are grouped into four pillars: a formal quality index; a static quality index; an activity-related quality index; and a performance-linked quality index. We then test the IAD index on a sample of Italian listed firms and conclude that there are significant associations (positive and negative) between the degree of compliance to some corporate governance regulations for listed firms and the IAD Index for the sample being considered.     

Evaluation of vectorization/parallelization techniques: application to nonparametric curve estimation

The simulation of statistical models in a computer is a fundamental aspect of research in the field of nonparametric curve estimation. Methods such as the FFT (Fast Fourier Transform) or WARP (Weighted Average of Rounded Points) have been developed and analysed for computer implementation of the different techniques in this realm, with the aim of reducing the computation time as much as possible. In this work we analyse two techniques with this objective. These are the vectorization of the source code in which the different algorithms are implemented, and their distributed execution. It can be observed that the vectorization of the programs can improve the results obtained with techniques such as the FFT or WARP, or, in some cases, can prevent the use of these.     

When Does Information about Probability Count in Choices Under Risk?

The question addressed in the present research is whether in naturalistic risky decision environments people are sensitive to information about the probability parameter. In Study 1, we showed that in naturalistic scenarios participants generally revealed little interest in obtaining information about the outcomes and probabilities. Moreover, participants asked fewer questions about probabilities for scenarios containing moral considerations. In Study 2, it was shown that, when supplied with information on probabilities, people could be sensitive to this information. This sensitivity depends on two factors. People were less sensitive to probabilities in scenarios perceived as containing ethical considerations. People were also less sensitive to probabilities when they were faced with a single-choice situation than when they were faced with a series of lotteries with different probabilities. This can be accounted for in terms of the evaluability principle.     

Community and social capital in Slovenia—the impact of transition

The transition from socialism to capitalism has many impacts on the everyday life of the people of Slovenia. Amongst others it has an impact on their community ties and their choices regarding participation in public life. Community can enable or diminish the basic processes, such as solidarity, equal choices and opportunities, and respect for the differences that are needed for an inclusive society. This article researches such processes through the concept of social capital and provides some responses necessary for the political and professional planning of social policy and the practice of social services.     

Poverty statics and dynamics: does the accounting period matter?

Any public policy aimed at reducing the effects of deprivation should be aware of the consequences of the use of different income accounting periods on eligibility and subsequent policy evaluation. This study aims to throw some light on the relev-ance of choosing a specific accounting period for public policy evaluation in a European country, in contrast to the existing evidence for the United States. Our analysis indicates that there are some significant differences in the results on poverty when using different income accounting periods. Researchers and decision-makers using an annual income measure, whatever the economic and social welfare context, should be aware that the use of quarterly data instead of yearly data will lead to a significantly larger number of poor households and a lower level of inequality and mobility in the distribution.     

Anabolic responses to resistance training in older men and women: a brief review

Resistance training has been shown to be the most effective exercise mode to induce anabolic adaptations in older men and women. Advances in imaging techniques and histochemistry have increased the ability to detect such changes, confirming the high level of adaptability that remains in aging skeletal muscle. This brief review presents a summary of the resistance-training studies that directly compare chronic anabolic responses to training in older (>60 years) men and women. Sixteen studies are summarized, most of which indicate similar relative anabolic responses between older men and women after resistance training. Relatively small sample sizes in most of the interventions limited their ability to detect significant sex differences and should be considered when interpreting these studies. Future research should incorporate larger sample sizes with multiple measurement time points for anabolic responses.