Utilizing Bayesian predictive power in clinical trial design

The Bayesian paradigm provides an ideal platform to update uncertainties and carry them over into the future in the presence of data. Bayesian predictive power (BPP) reflects our belief in the eventual success of a clinical trial to meet its goals. In this paper we derive mathematical expressions for the most common types of outcomes, to make the BPP accessible to practitioners, facilitate fast computations in adaptive trial design simulations that use interim futility monitoring, and propose an organized BPP-based phase II-to-phase III design framework.     

Optimal and lead-in adaptive allocation for binary outcomes: A comparison of Bayesian methods

We compare posterior and predictive estimators and probabilities in response-adaptive randomization designs for two- and three-group clinical trials with binary outcomes. Adaptation based upon posterior estimates are discussed, as are two predictive probability algorithms: one using the traditional definition, the other using a skeptical distribution. Optimal and natural lead-in designs are covered. Simulation studies show that efficacy comparisons lead to more adaptation than center comparisons, though at some power loss, skeptically predictive efficacy comparisons and natural lead-in approaches lead to less adaptation but offer reduced allocation variability. Though nuanced, these results help clarify the power-adaptation trade-off in adaptive randomization.     

Decomposing primary and secondary effects: A new decomposition method

One strand of educational inequality research aims at decomposing the effect of social class origin on educational choices into primary and secondary effects. We formalize this distinction and present a new and simple method that allows empirical assessment of the relative magnitudes of primary and secondary effects. Contrary to other decomposition methods, this new method is unbiased, is more intuitive, and decomposes effects of both discrete and continuous measures of social origin. The method also provides analytically derived statistical tests and is easily calculated with standard statistical software. We give examples using the Danish Longitudinal Survey of Youth.     

Gender and racial/ethnic differences in predicting adolescent sexual risk: athletic participation versus exercise

Though often conflated, informal physical exercise and organized athletic participation have very different implications for adolescent sexual risk outcomes. The purpose of this research is to disaggregate strenuous exercise from sports, examine how each is associated with sexual risk, and explain the observed differences using the conceptual lens of cultural resource theory. Using a nationally representative sample of over 16,000 public and private high school students, we employ logistic regression to test hypotheses about the gender-specific and race-specific effects of strenuous exercise and athletic participation on adolescent sexual risk behavior. The results show that both forms of physical activity buffer sexual risk for girls. Strenuous exercise is associated with increased odds of sexual risk for boys. Sports and race interact to influence boys' sexual risk outcomes: Athletic participation is associated with lowered odds of sexual risk for white male adolescents, but heightened odds of sexual risk for black male adolescents.     

冒险成就的电信巨头

从任何一个角度看,全球无线手机通讯行业都在快速逼近危机的边缘。全世界已经有50多个国家的手机用户数量超过其实际人口数量。即使是在工业化国家中手机人均拥有率较低的美国,在用的手机数量也超过了2.7亿部（市场渗透率接近于90％）。今天,随着无线通讯市场的日益萎缩,     

Role of motives and attributes in consumer motion picture choice

The study focuses on consumer motion picture motives and choice criteria. Its purpose can be specified into the following objectives: (1) to examine the motivational basis of cinema attending. (2) to examine the predictive ability of movie motives and consumers' attribute importances in preference regressions of four types of movie, (3) to carry out a motion picture choice analysis by predicting audience membership with discriminant analysis. The data is based on a convinience sample of Finnish consumers (N = 228) attending one of the following types of movie: adventures/ thrillers, human/ social dramas, sex movies, entertainment movies.The results of a group of multivariate analyses (factor analysis, canonical correlation, preference regression, and discriminant analysis) indicate that consumers attending different types of films have distinctly separate motivation bases, as well as attribute importance profiles, underlying their movie choices. Each movie type had a specific preference structure, expressed by the regression coefficients. Finally, the discriminant analysis suggests that the general motive and attribute variables are effective also in predicting motion picture choice. On balance, the results were mutually supportive and exemplify the managerial usefulness of quantitative consumer analysis also in the case of such abstract leisure products as motion pictures.     

Soft cultures: the symbolism of cross-border organizing 1

It is not always true that the concept of culture implies a convergence on one meaning, one set of values, one pattern of behaviour. This paper develops the notion of soft culture. Cultures are soft in the sense that multiple renderings of reality are accepted and legitimized. Soft culture is studied in the context of cross-national technology development projects. Such projects are loosely structured communities, as organizational actors are separated in time and space. The paper demonstrates how symbols work among those actors. In addition to the traditional uses of symbolic categorizing, in soft culture the symbols also play an important role in attracting more networks to the action and licensing a wide variety of exploratory activities. These equivocal characteristics of symbols should be considered a strength in face of overwhelming uncertainty since they allow actors to construct multiple futures and pursue them.     

The accuracy of normal approximation in a heterogeneous panel data unit root test

Tests for unit roots in panel data have become very popular. Two attractive features of panel data unit root tests are the increased power compared to time-series tests, and the often well-behaved limiting distributions of the tests. In this paper we apply Monte Carlo simulations to investigate how well the normal approximation works for a heterogeneous panel data unit root test when there are only a few cross sections in the sample. We find that the normal approximation, which should be valid for large numbers of cross-sectional units, works well, at conventional significance levels, even when the number of cross sections is as small as two. This finding is valuable for the applied researcher since critical values will be easy to obtain and p-values will be readily available.     

Jocks, gender, race, and adolescent problem drinking

Alcohol remains the drug of choice for many adolescents; however, the nature of the relationship between athletic involvement and alcohol misuse remains ambiguous. In this article, we used a longitudinal sample of over 600 Western New York adolescents and their families to explore the gender-specific and race-specific relationships between identification with the "jock" label and adolescent alcohol consumption, specifically problem drinking. Operationalization of problem drinking included frequency measures of heavy drinking, binge drinking, and social problems related to alcohol (e.g., trouble with family, friends, school officials over drinking). Self-identified adolescent "jocks" were more likely to engage in problem drinking than their non-jock counterparts, even after controlling for gender, age, race, socioeconomic status, physical maturity, social maturity, and frequency of athletic activity. Jock identity was strongly associated with higher binge drinking frequency in Black adolescent girls. This study underscores the need to distinguish between objective and subjective meanings of athletic involvement when assessing the relationship between sport and adolescent health-risk behavior.     

Characteristics of men and women who complete or exit from an on-line internet sexuality questionnaire: a study of instrument dropout biases

This study compared respondents who completed an Internet sexuality questionnaire and those who dropped out before completion. The study was in Swedish and comprised 3,614 respondents over a 2-week period (53% males, 47% females). There were significant differences between males, of whom 51% dropped out before completion of the 175-item questionnaire, and females, of whom 43% dropped out. Dropout in both genders followed a curve of negative acceleration. The data suggest that dropout is likely to be significant and gender and demographically biased, and to occur significantly earlier for men than for women. Geography, education, sexual orientation, age, relationship status, living arrangements, and Internet connection speed were related to dropout for men, while only relationship status and living arrangements, which were in the opposite direction from men, were related to dropout in women.