From case management to prevention of scientific dishonesty in Denmark

In 1992, The Danish Medical Research Council established a national committee on scientific dishonesty with the twofold task of handling cases of scientific misconduct and taking preventive initiatives. Scientific dishonesty was proven in only five cases, but in another nine cases lesser degrees of deviations from good scientific practice were found. The experiences from a total of 24 treated cases indicated that three key areas were at the basis of most of the accusations and the deviations from good practice: uncertainty about 1) authorship, about 2) rights and duties to use scientific data and about 3) agreements at the initiation of joint studies. As a consequence guidelines on good practice have been issued on these key subjects. An earlier version of this paper was presented at a symposium, Scientific Misconduct. An International Perspective, organised by The Medical University of Warsaw, 16 November, 1998.     

Index of suspicion: feeling not believing

Throughout the U.S., state laws require professionals who work with children to report cases of suspected child abuse to child protection services. Both practically and conceptually, however, significant problems arise from a lack of clarity regarding the threshold that has been set for reporting. Specifically, there is no consensus as to what constitutes reasonable suspicion, and little direction for how mandated reporters should gauge their legal and professional responsibilities when they harbor suspicion. In this paper we outline the context of the problem, discuss the nature and scope of its conceptual underpinnings, and offer recommendations for moving towards a concrete, practical solution.     

Tucker3 hierarchical classes analysis

This paper presents a new model for binary three-way three-mode data, called Tucker3 hierarchical classes model (Tucker3-HICLAS). This new model generalizes Leenen, Van Mechelen, De Boeck, and Rosenberg's (1999) individual differences hierarchical classes model (INDCLAS). Like the INDCLAS model, the Tucker3-HICLAS model includes a hierarchical classification of the elements of each mode, and a linking structure among the three hierarchies. Unlike INDCLAS, Tucker3-HICLAS (a) does not restrict the hierarchical classifications of the three modes to have the same rank, and (b) allows for more complex linking structures among the three hierarchies. An algorithm to fit the Tucker3-HICLAS model is described and evaluated in an extensive simulation study. An application of the model to hostility data is discussed.The first author is a Research Assistant of the Fund for Scientific Research-Flanders (Belgium). The research reported in this paper was partially supported by the Research Council of K.U. Leuven (GOA/2000/02). We are grateful to Kristof Vansteelandt for providing us with an interesting data set.     

Shackling the shoulders of giants

This paper informally summarizes a two-day symposium held at the U.S. National Academy of Sciences in Washington, D.C., September 5–6, 2002. The issue was to what extent the progress of science and societal capacity for continued technological innovation are threatened by excessive protection of intellectual property. Excessive protection creates disadvantages not only for scientists and inventors but also for educators/students and for librarians/clientele. Speakers from a variety of disciplines and institutions agreed unanimously that scientific and technological progress is, indeed, under serious threat. Various opinions were expressed about the degree of threat, currently and prospectively, as well as what counter-measures are best suited to resist undue restrictions on creative uses of scientific and technical data and information. This summary is based entirely on the author’s notes from the symposium, and the commentary offered is his alone. My apologies to the speakers if this paper does not accurately reflect the primary intent of their presentations. The “Suggested Readings” offered at the end are not specific to the speakers’ statements but rather are offered as a general resource to aid further research. The definitive record of the symposium is planned to be available from the National Academies Press as a Proceedings publication in the summer of 2003. John Gardenier is an independent researcher, ethicist and science writer.     

Constrained maximum likelihood estimation of two-level covariance structure model via EM type algorithms

In this paper, the constrained maximum likelihood estimation of a two-level covariance structure model with unbalanced designs is considered. The two-level model is reformulated as a single-level model by treating the group level latent random vectors as hypothetical missing-data. Then, the popular EM algorithm is extended to obtain the constrained maximum likelihood estimates. For general nonlinear constraints, the multiplier method is used at theM-step to find the constrained minimum of the conditional expectation. An accelerated EM gradient procedure is derived to handle linear constraints. The empirical performance of the proposed EM type algorithms is illustrated by some artifical and real examples.This research was supported by a Hong Kong UCG Earmarked Grant, CUHK 4026/97H. We are greatly indebted to D.E. Morisky and J.A. Stein for the use of their AIDS data in our example. We also thank the Editor, two anonymous reviewers, W.Y. Poon and H.T. Zhu for constructive suggestions and comments in improving the paper. The assistance of Michael K.H. Leung and Esther L.S. Tam is gratefully acknowledged.     

Predicting elections from the most important issue: A test of the take‐the‐best heuristic

We used the take‐the‐best heuristic to develop a model to forecast the popular two‐party vote shares in U.S. presidential elections. The model draws upon information about how voters expect the candidates to deal with the most important issue facing the country. We used cross‐validation to calculate a total of 1000 out‐of‐sample forecasts, one for each of the last 100 days of the ten U.S. presidential elections from 1972 to 2008. Ninety‐seven per cent of forecasts correctly predicted the winner of the popular vote. The model forecasts were competitive compared to forecasts from methods that incorporate substantially more information (e.g., econometric models and the Iowa Electronic Markets). The purpose of the model is to provide fast advice on which issues candidates should stress in their campaign. Copyright © 2010 John Wiley & Sons, Ltd.     

Commentary on “Mediation analysis and categorical variables: The final frontier” by Dawn Iacobucci

The commentary discusses several topics in Dr. Iacobucci's article on mediation analysis with categorical variables including the lack of equivalency of mediated effect measures, ab, and c–c′, that are algebraically equivalent in ordinary least squares regression models. The commentary raises the issue of correlated mediation coefficients and presents formulas to include the correlation in the test of significance. References to new developments in causal mediation analysis for categorical variables are given and the importance of programs of research to establish a mediation theory is emphasized.     

CREATING AN IPHONE APPLICATION FOR COLLECTING CONTINUOUS ABC DATA

This paper provides an overview and task analysis for creating a continuous ABC data‐collection application using Xcode on a Mac computer. Behavior analysts can program an ABC data collection system, complete with a customized list of target clients, antecedents, behaviors, and consequences to be recorded, and have the data automatically sent to an e‐mail account after observations have concluded. Further suggestions are provided to customize the ABC data‐ collection system for individual preferences and clinical needs.     

Introducing naturalistic cycling data: What factors influence bicyclists’ safety in the real world?

Presently, the collection and analysis of naturalistic data is the most credited method for understanding road user behavior and improving traffic safety. Such methodology was developed for motorized vehicles, such as cars and trucks, and is still largely applied to those vehicles. However, a reasonable question is whether bicycle safety can also benefit from the naturalistic methodology, once collection and analyses are properly ported from motorized vehicles to bicycles. This paper answers this question by showing that instrumented bicycles can also collect analogous naturalistic data. In addition, this paper shows how naturalistic cycling data from 16 bicyclists can be used to estimate risk while cycling. The results show that cycling near an intersection increased the risk of experiencing a critical event by four times, and by twelve times when the intersection presented some form of visual occlusion (e.g., buildings and hedges). Poor maintenance of the road increased the risk tenfold. Furthermore, the risk of experiencing a critical event was twice as large when at least one pedestrian or another bicyclist crossed the bicyclist’s trajectory. Finally, this study suggests the two most common scenarios for bicycle accidents, which result from different situations and thus require different countermeasures. The findings presented in this paper show that bicycle safety can benefit from the naturalistic methodology, which provides data able to guide development and evaluation of (intelligent) countermeasures to increase cycling safety.     

Satisfaction et confort au travail. L’apport de la démarche implicative

A large body of research has investigated the psycho-organizational variables predicting satisfaction at work, but few studies have so far examined variables in the field of environmental psychology. Our study aims first to identify the impact of variables evaluating comfort at work (satisfaction with the work environment, attachment to the workplace) by comparing them with organizational variables known to be related to job satisfaction, and then to rank the relationships between these variables in a pseudo- implication sequence, based on statistical implicative analysis. The study involved 105 bank employees and confirms our theoretical model, showing that job satisfaction can be explained implicatively by the three other variables [(Comfort/Functionality => Control/privacy) => Workplace attachment] => job satisfaction.