Inference and Decision Making for 21st-Century Drug Development and Approval

ABSTRACT

The cost and time of pharmaceutical drug development continue to grow at rates that many say are unsustainable. These trends have enormous impact on what treatments get to patients, when they get them and how they are used. The statistical framework for supporting decisions in regulated clinical development of new medicines has followed a traditional path of frequentist methodology. Trials using hypothesis tests of “no treatment effect” are done routinely, and the p-value < 0.05 is often the determinant of what constitutes a “successful” trial. Many drugs fail in clinical development, adding to the cost of new medicines, and some evidence points blame at the deficiencies of the frequentist paradigm. An unknown number effective medicines may have been abandoned because trials were declared “unsuccessful” due to a p-value exceeding 0.05. Recently, the Bayesian paradigm has shown utility in the clinical drug development process for its probability-based inference. We argue for a Bayesian approach that employs data from other trials as a “prior” for Phase 3 trials so that synthesized evidence across trials can be utilized to compute probability statements that are valuable for understanding the magnitude of treatment effect. Such a Bayesian paradigm provides a promising framework for improving statistical inference and regulatory decision making.     

The Electoral College and Conflict in American History and Politics

The historical relationship between the electoral college and controversial U.S. presidential elections, specifically with respect to conflict, is examined. The elections of 1800, 1824, 1860, 1876, 1888, 1968, and 2000 are examined. Aside from the 2000 election, there has been essentially no conflict in American history due to the electoral college. The constitutional structure and thinking behind the form of the electoral college is given, with emphasis on the federal aspects of the structure. The current movement to abolish the electoral college in favor of direct popular vote is depicted, along with the arguments against making that change. The conclusion is that we as a nation are far better off to retain the status quo than to make the called-for change.     

The Relationship Between Sense of Coherence and Career Thoughts

The authors examined the impact of sense of coherence on the career thought processes of a sample of college students. A. Antonovsky (1987) defined sense of coherence as the global orientation that the world is comprehensible, manageable, and meaningful. Study participants completed the Sense of Coherence Scale (A. Antonovsky, 1987) and the Career Thoughts Inventory (CTI; J. P. Sampson, G. W. Peterson, J. G. Lenz, R. C. Reardon, & D. E. Saunders, 1996). Multivariate tests indicated a medium relationship between sense of coherence and CTI Total and subscale scores; sense of coherence accounted for 14% of the variance. Univariate tests also indicated a medium relationship between sense of coherence and each subscale.     

Adolescent Protective Factors Promoting Resilience in Young Adults at Risk for Depression

In a longitudinal, community-based study, adolescent protective factors for those at risk for depression were identified that were associated with resilient outcomes in young adulthood. For those with childhood risk factors for major depression, significant protective factors included family cohesion, positive self appraisals, and good interpersonal relations. Findings may help inform the development of prevention and treatment programs for adolescents vulnerable to depression. Implications for future research and clinical practice are discussed.     

Fire and restoration of the largest urban forest of the world in Rio de Janeiro City,Brazil

National Park of Tijuca in Rio de Janeiro (Brazil) is about 3,300 ha and considered the largest urban forest in the world. Its floristic composition is typical of Atlantic Rain Forest. The reserve is being altered because of fire occurrences and urban expansion. This study identified locations and causes of forest fires, and makes management recommendations to restore damaged areas. From 1991 to 2000, forest firefighters recorded an average of 75-fire occurrences/year. Identified causes included hot air balloons (24%), intentional (24%), rubbish burning (21%) and religious practices (17%). Primary fuels included invasive grasses and ferns. Although hot air balloons destroyed larger areas of forest in each occurrence, a greater number of fires started in the invasive vegetation along roads that bisect the forest. In response to recurrent forests, invasive vegetation has spread gradually into the forest increasing forest degradation. To decrease fire damage, sites with high fire frequencies and density of invasive vegetation were planted with less flammable species. Results indicate that fire frequency decreased and density of invasive vegetation declined. This approach appears to prevent fire incidence, reduce the need for fire fighting, and preserve existing biodiversity.     

Dairy Farm Survival in a Metropolitan Area: Dutchess County,New York, 1984–19901

Abstract The effect of nonfarm development on dairy farm survival in New York's highly developed lower Hudson Valley is analyzed. The major hypothesis is that significant losses of dairy farms during this period are the result of urban development pressures. Contrary to this hypothesis, however, the bivariate and multivariate analyses of data from a mail survey of all commercial dairy operators in Dutchess County as of 1984 and industry survivors, exiters, and new entrants through 1990 demonstrate that nonfarm development has a negligible effect on dairy farm survival; rather, survival is significantly affected by age of operator and by family disruption. Thus, demographic and family process factors are found to be more powerful determinants of dairy farm survival in this particular metropolitan context.     

Bayesian analysis of mixture modelling using the multivariate t distribution

A finite mixture model using the multivariate t distribution has been shown as a robust extension of normal mixtures. In this paper, we present a Bayesian approach for inference about parameters of t-mixture models. The specifications of prior distributions are weakly informative to avoid causing nonintegrable posterior distributions. We present two efficient EM-type algorithms for computing the joint posterior mode with the observed data and an incomplete future vector as the sample. Markov chain Monte Carlo sampling schemes are also developed to obtain the target posterior distribution of parameters. The advantages of Bayesian approach over the maximum likelihood method are demonstrated via a set of real data.