Simple and multiple correspondence analysis for ordinal-scale variables using orthogonal polynomials

Correspondence analysis (CA) has gained a reputation for being a very useful statistical technique for determining the nature of association between two or more categorical variables. For simple and multiple CA, the singular value decomposition (SVD) is the primary tool used and allows the user to construct a low-dimensional space to visualize this association. As an alternative to SVD, one may consider the bivariate moment decomposition (BMD), a method of decomposition that involves using orthogonal polynomials to reflect the structure of ordered categorical responses. When the features of BMD are combined with SVD, a hybrid decomposition (HD) is formed. The aim of this paper is to show the applicability of HD when performing simple and multiple CA.     

Adaptive Confidence Intervals for the Test Error in Classification

The estimated test error of a learned classifier is the most commonly reported measure of classifier performance. However, constructing a high quality point estimator of the test error has proved to be very difficult. Furthermore, common interval estimators (e.g. confidence intervals) are based on the point estimator of the test error and thus inherit all the difficulties associated with the point estimation problem. As a result, these confidence intervals do not reliably deliver nominal coverage. In contrast we directly construct the confidence interval by use of smooth data-dependent upper and lower bounds on the test error. We prove that for linear classifiers, the proposed confidence interval automatically adapts to the non-smoothness of the test error, is consistent under fixed and local alternatives, and does not require that the Bayes classifier be linear. Moreover, the method provides nominal coverage on a suite of test problems using a range of classification algorithms and sample sizes.     

American Statistical Association's Section on Physical and Engineering Sciences: Past,Present, and Future

This article is also one of the section's contributions to the celebration of the sesquicentennial of the American Statistical Association (ASA). It describes the early history of the section, discusses activities of the section in the 1960s, 1970s, and 1980s as a principal component of ASA, and offers a prospectus for the section in the 1990s.     

Predicting adult health and mortality from adolescent facial characteristics in yearbook photographs

Several important longitudinal studies in the social sciences have omitted biomarkers that are routinely recorded today, including height and weight. To account for this shortcoming in the Wisconsin Longitudinal Study (WLS), an 11-point scale was developed to code high school senior class yearbook photographs of WLS participants for relative body mass (RBM). Our analyses show that although imperfect, the RBM scale is reliable (α = .91) and meets several criteria of validity as a measure of body mass. Measured at ages 17–18, the standardized relative body mass index (SRBMI) was moderately correlated (r = .31) with body mass index (BMI) at ages 53–54 and with maximum BMI reported between ages 16 and 30 (r = .48). Overweight adolescents (≥ 90th percentile of SRBMI) were about three times more likely than healthy-weight adolescents (10th–80th percentile of SRBMI) to be obese in adulthood and, as a likely consequence, significantly more likely to report health problems such as chest pain and diabetes. Overweight adolescents also suffered a twofold risk of premature death from all nonaccidental causes as well as a fourfold risk of heart disease mortality. The RBM scale has removed a serious obstacle to obesity research and lifelong analyses of health in the WLS. We suggest that other longitudinal studies may also be able to obtain photos of participants at younger ages and thus gain a prospectively useful substitute for direct measures of body mass.     

Energy Use in Institutional Buildings: Estimates From State Energy-Audit Surveys

This article examines the determinants of energy demand for nearly 9,000 institutional buildings in the United States. The data were collected, as part of the federal Institutional Conservation Program, by state energy offices using mail surveys. The article presents energy demand estimates adjusted for differences in state surveys as well as for nonresponse bias, as functions of energy prices, building characteristics, and fuel-type variables for approximations of the installed heating ventilation and air-conditioning equipment. Energy price elasticities are found to vary from ?.28 for schools to ?1.05 for hospitals.     

Personnel turnover in health care organizations: Test of a predictive model based on work assessments by employees

Abstract

It is predicted that institutions in Dutch intramural health care will be increasingly confronted with problems in personnel supply. Instead of making great efforts to keep the inflow of new personnel on the desired level, control of turnover is an alternative solution. In this paper, an explanatory model is constructed, based on previous theories and research findings. It is hypothesized that the more employees have positive attitudes concerning their work and work situation, the greater their satisfaction and commitment and hence the less their intention to leave and the lower actual turnover. This model was tested using a large scale employee questionnaire. The instrument turned out to be reliable (internal consistencies above .70). The questionnaire was administered in eight institutions in four health care sectors (n = 1456). Results indicate that attitudes about work content and personnel management are relevant in predicting intention to leave. All in all, 8 work-related aspects predicted 21% of intention to leave. Aspects with the most predictive value were career guidance, work safety, responsibilities and job discretion. Furthermore, general satisfaction was shown to play an intermediary role in predicting intention to leave. It is concluded that improvements in work content and personnel management can reduce intention to leave and hence the demand for new personnel.     

'Woman,Speak with a Loud Voice!'

This paper seeks to contribute to the critique of mainstream development discourse by conveying the ideas and issues raised by rural South African women. Building upon feminist and post-colonial discourses, this paper shifts the epistemological location of knowing to the women affected by development programmes and policies. Based upon interviews and discussions with over 600 women in rural communities, we offer a brief characterization of the South African context of rural women's lives, followed by rural women's comments about development, their daily struggles, and empowerment. Rural women's comments reveal a conception of development that is tied to their localized problem-solving skills and opportunities. Their response to the absence of development opportunities within their communities is to forge a space where they can negotiate between institutional spheres of power in order to address their needs. We argue that traditional development approaches overlook the space, or interstice, rural African women occupy between the modern state and traditional authority. For persons interested in development issues, rural women's experiences direct our attention to the in-between spaces as potential sites of empowerment.