Search

We investigate what fraction of all significant results in website A/B testing is actually null effects (i.e., the false discovery rate (FDR)). Our data consist of 4,964 effects from 2,766 experiments conducted on a commercial A/B testing platform. Using three different methods, we find that the FDR ranges between 28% and 37% for tests conducted at 10% significance and between 18% and 25% for tests at 5% significance (two sided). These high FDRs stem mostly from the high fraction of true null effects, about 70%, rather than from low power. Using our estimates, we also assess the potential of various A/B test designs to reduce the FDR. The two main implications are that decision makers should expect one in five interventions achieving significance at 5% confidence to be ineffective when deployed in the field and that analysts should consider using two-stage designs with multiple variations rather than basic A/B tests. This paper was accepted by Eric Anderson, marketing. [ABSTRACT FROM AUTHOR]

In this paper, Kruskal-Wallis test is extended to deal with neutrosophic data in single valued form using score, accuracy and certainty functions to calculate ranks of SVNNs, also Mann-Whitney test is extended to deal with same data type which makes it possible to do a post-hoc test after rejecting null hypothesis using Neutrosophic Statistics Kruskal-Wallis test. Numerical examples were successfully solved showing the power of this new idea to deal with SVNNs and make statistical decisions on them. [ABSTRACT FROM AUTHOR]

Statistical methods are indispensable to the practice of science. But statistical hypothesis testing can seem daunting, with P-values, null hypotheses, and the concept of statistical significance. This article explains the concepts associated with statistical hypothesis testing using the story of "the lady tasting tea," then walks the reader through an application of the independent-samples t-test using data from Peter and Rosemary Grant's investigations of Darwin's finches. Understanding how scientists use statistics is an important component of scientific literacy, and students should have opportunities to use statistical methods like this in their science classes. [ABSTRACT FROM AUTHOR]

This study compares husbands' and wives' views on the person in a couple who should be responsible for preparing for hurricane hazards; it also examines whether the varying levels of agreement reached by husbands and wives regarding this responsibility are associated with actual preparedness behaviors. An online survey targeting married, heterosexual couples living in Sarasota County, Florida, USA was sent out between March and May, 2015. Both the husbands and the wives were asked to fill out the survey. A total of 170 surveys were used for analysis. Results suggested that husbands and wives felt that they had shared responsibility for most of the 19 preparedness behaviors considered. However, a few stereotypically masculine preparedness behaviors were found to typically fall to husbands. Husbands' and wives' views of perceived responsibility were not statistically different, but husbands tended to favor individual responsibility, while wives tended to favor joint responsibility. Higher levels of agreement were significantly associated with greater engagement in planning-related preparedness behaviors. Policy implications are discussed. [ABSTRACT FROM AUTHOR]

The article presents the study that explores on the use of haematopoietic stem cell transplantation (SCT) in the treatment of Fanconi anemia (FA) patients in Canada and the U.S. The topics discussed include the attributes of FA, the factors that influenced the decision making of FA patients and family members on SCT, and the benefits and probable risks of SCT.

Background: Recent frameworks for understanding food rewards recognize the role of separable affective and motivational processes (liking and wanting) in driving human eating behavior. Separate assessments of liking and wanting may aid in understanding the complex eating-related behaviors seen in anorexia nervosa (AN). Objective: The aim of this study was to examine separately liking and wanting for foods of different energy densities in women at different stages of AN and in healthy volunteers at both an implicit and an explicit level. Design: Explicit liking and wanting responses to high- and low-calorie foods were derived from analog ratings, whereas an implicit "wanting" measure was identified by using reaction time in a forced-choice procedure. Explicit and implicit processes were compared across 3 groups of AN participants (current AN, weight-restored AN, and recovered AN) and healthy volunteers. Results: Currently underweight AN participants explicitly wanted high-calorie foods less than did the other groups. Both current and weight-restored AN groups demonstrated significantly less implicit "wanting" for high-calorie foods and more implicit "wanting" for low-calorie foods--an inverted pattern to never-ill participants. Conclusions: The aberrant responses to food that characterize AN may be driven more by altered motivational salience ("wanting") than by explicit liking responses. This pattern of aberrant food reward appears to be independent of weight status. Examining the processes that motivate approach or avoidance of low- and high-calorie foods in AN may aid the development of targeted strategies to augment existing interventions. [ABSTRACT FROM AUTHOR]

Background Socioeconomically deprived women are at greater risk of adverse pregnancy outcomes. Research tends to focus on access of services. Yet access may not equate with the equity of services for women from different socioeconomic backgrounds. Objectives To determine whether pregnant women's perceptions of antenatal provision differed in relation to their socioeconomic deprivation ranking (determined by the Scottish Index of Multiple Deprivation 2006). Design A longitudinal, qualitative study with comparative antenatal case studies between January 2007 and April 2009. Setting/Participants Cases were primigravida women from 'least deprived' ( n = 9) and 'most deprived' ( n = 12) geographical areas within one local authority in Scotland. Analysis Data were analysed using case study replication analysis. Results There was little difference in access to antenatal services between the 'least' and 'most' deprived groups. Perception of care differed in relation to the level of 'engagement' (defined using constructs of: language and personalization of care; power and relationships; and health literacy). Engagement was evidenced in most of the 'least deprived' cases and almost none of the 'most deprived' cases. Specifically, socioeconomically deprived women described less evidence of personal connection to their own care, effective communication and the opportunity for shared decision making. Conclusion In women from socioeconomically deprived areas, access may be a less useful indicator than engagement when assessing antenatal service quality. As engagement levels may be one method by which to predict and improve health outcomes, a more equitable antenatal service may need to be developed through the early identification of those women at risk of non-engagement. [ABSTRACT FROM AUTHOR]

Context and objective Shared decision making is especially advocated for preference-sensitive decisions. We investigated whether physicians' recommendations pull patients away from their preferred treatment option when making a preference-sensitive decision. Design, participants and methods Inpatients ( N = 102 with schizophrenia, N = 101 with multiple sclerosis) were presented with a hypothetical scenario (the choice between two drugs). They were first asked about their preferences concerning the two drugs and then they received a (fictitious) clinician's recommendation that was contrary to their preferences. Subsequently they made a final choice between the two drugs. Main outcome measures The main outcome measure was whether the patient followed the physician's advice in the hypothetical scenario. Thereby patient's (pre-recommendation) preferences served as a baseline. Results In the decision scenario, about 48% of the patients with schizophrenia and 26% of the patients with multiple sclerosis followed the advice of their physician and thus chose the treatment option that went against their initial preferences. Patients who followed their physician's advice were less satisfied with their decision than patients not following their physician's advice (schizophrenia: t = 2.61, P = 0.01; multiple sclerosis: t = 2.67, P = 0.009). Discussion and conclusions When sharing decisions with patients, physicians should be aware that their advice might influence patients' decisions away from their preferred treatment option. They should encourage their patients to identify their own preferences and help to find the treatment option most consistent with them. [ABSTRACT FROM AUTHOR]

Consider a standard statistical hypothesis test, leading to a binary decision made by exploiting a certain dataset. Suppose that, later, part of the data is lost, and we want to refine the test by exploiting both the surviving data and the previous decision. What is the best one can do? Such a question, here referred to as the unlucky broker problem, can be addressed by very standard tools from detection theory, but the solution gives intriguing insights and is by no means obvious. We provide the general form of the optimal detectors and discuss in depth their modus operandi, ranging from simple likelihood ratio tests to more complex behaviors. Limiting cases, where either the surviving data or the initial decision is almost useless, are also discussed. [ABSTRACT FROM AUTHOR]

Copyright of Revista Daena: International Journal of Good Conscience is the property of Spenta University Mexico and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Revista Daena: International Journal of Good Conscience is the property of Spenta University Mexico and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

We consider the scenario where additive, independent, and identically distributed (i.i.d) noise in an image is removed using an overcomplete set of linear transforms and thresholding. Rather than the standard approach, where one obtains the denoised signal by ad hoc averaging of the denoised estimates provided by denoising with each of the transforms, we formulate the optimal combination as a conditional linear estimation problem and solve it for optimal estimates. Our approach is independent of the utilized transforms and the thresholding scheme, and as we illustrate using oracle-based denoisers, it extends established work by exploiting a separate degree of freedom that is, in general, not reachable using previous techniques. Our derivation of the optimal estimates specifically relies on the assumption that the utilized transforms provide sparse decompositions. At the same time, our work is robust as it does not require any assumptions about image statistics beyond sparsity. Unlike existing work, which tries to devise ever more sophisticated transforms and thresholding algorithms to deal with the myriad types of image singularities, our work uses basic tools to obtain very high performance on singularities by taking better advantage of the sparsity that surrounds them. With well-established transforms, we obtain results that are competitive with state-of-the-art methods. [ABSTRACT FROM AUTHOR]

In recent work we introduced a general, a weak, and a strong partitioning principles for the construction of multiple decision procedures as multiple testing or selection procedures. Partitioning principles can be viewed as natural extensions of the closure principle and sometimes yield more powerful decision procedures. In this article we consider the problem of establishing equivalence with the best with respect to k treatment means, where equivalence is defined in terms of a threshold value δ > 0. We reformulate the original selection problem as a multiple testing problem and develop various step-down and step-up procedures by applying the closure principle and partitioning principles. The new step-down procedure is shown to provide a uniform improvement over procedures currently in use. Moreover, we propose some projection methods that yield confidence intervals being compatible with stepwise tests and selection procedures. [ABSTRACT FROM AUTHOR]

The crucial steps in a quantitative analysis of a decision problem are problem formulation, model building, analysis, and implementation. Given an initial model specification, the goal of analysis is to determine the values of the controllable or decision variables that optimize the objective function. Frequently the initial model is inadequate and must be reformulated. While modeling is an evolutionary process involving art and science, under certain conditions Response Surface Methodology (RSM) is an effective vehicle for constructing and parameterizing optimization models. RSM, which draws upon the areas of experimental design, modeling, inference, and optimization, utilizes different opening and ending strategies. Through simultaneous and sequential experimentation, the approximate region of the model's maximum response is found by employing the steepest ascent method. Subsequently, the exact values of the controllable variables that maximize the model's response are determined by canonical analysis. The RSM concepts are first developed within the context of a manufacturing problem. A potential application to simulation studies is then presented. [ABSTRACT FROM AUTHOR]

In an earlier paper [5] the authors compared the power of the BLUS test with the probability of a correct decision of the Durbin-Watson bounds test. A method to compute the distribution of the Von Neumann ratio under the null hypothesis and under the alternative hypothesis was given. In the present paper the latter method is used to tabulate the BLUS-test statistic and to compute the exact significance points of the Durbin-Watson test for several examples. Powers of both tests are computed and compared. It appears that, for the cases considered, the power of the exact Durbin-Watson test exceeds that of the BLUS procedure, while the latter is greater than the probability of a correct decision in the Durbin-Watson bounds test. [ABSTRACT FROM AUTHOR]