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.     

Determinanten regelkonformen Verhaltens am beispiel des Strassenverkehrs

The main role of traffic police enforcement can be seen as preventing road users from committing offences, which can be related to road crashes and injuries. As the operating principle underlying the impact of police enforcement a deterrence effect has been discussed repeatedly, whereas from a sociological perspective the importance of “Norm Internalisation” has been emphasised. Thus, the present paper aims at comparing the influence of “Norm Internalisation” and the variables constituting the deterrence effect on the compliance with rules in road traffic. Based on a secondary analysis of data from a project on behavioural determinants of police surveillance carried out by the “Institute of Applied Transport and Tourism Research” (IVT) on behalf of the Federal Highway Research Institute (BASt) an operationalisation of the construct “General Norm Orientation” is developed. In several subsequent steps of statistical analysis patterns of correlations with variables from Opp’s “Theory of Law Obedience” are revealed. Results show a sufficiently high internal consistency (α = 0,82) of the scale “General Norm Orientation” and significant correlations with variables from Opp’s theory. The directions of these correlations are as expected and confirmed by multivariate analyses. Results are discussed with respect to their implications for influencing road users’ behaviours.     

‚The Good, the Bad, and the Ugly‘

According to the most influential contribution of recent years to the comparative study of advanced welfare states, Esping-Andersen’s ’Three Worlds of Welfare Capitalism‘, the welfare state basically comes in three variants: as a social-democratic, a conservative, or as a liberal regime. Yet, at a closer look, in particular the ’conservative‘ regime-type represents a highly problematic category. The article claims that the major problems of Esping-Andersen’s typology and theory originate from his sole focus on the class conflict and his neglect of the religious cleavage. Major theoretical contradictions and empirical puzzles of his approach can be solved if we take not only the impact of the catholic social doctrine on the development of the welfare state into account, but consider also the influence of social protestantism, especially that of protestant dissent and of protestant non-conformism. The paper substantiates this claim with data for the early formative period of the welfare state (1890–1920) as well as for the high-time of the welfare state from the 1960s to the 1990s.     

Generationswechsel im Management ost- und westdeutscher Unternehmen

Currently, in the top-management of German enterprises a generational shift is taking place. The paper looks at the consequences of this change concerning the future of the ‘German model of capitalism’. Are the managers of the new generation still holding on to the traditional German management culture or are they orienting themselves more strongly towards the US-American shareholder-value model? In order to clarify this question, the existing empirical results of management research are systematically evaluated. According to the results of this analysis we are not going to face a far-reaching Americanization of the management culture. However, under the pressure of globalization a significant differentiation between management culture in large enterprises on the one hand and management culture in small and medium-sized enterprises on the other hand occurs. While managers of large enterprises adopt elements of the American management model to a great degree, German management seems to become even more accentuated in the culture of small and medium-sized enterprises. In the context of this recent development existing differences between the management in Eastern and Western German enterprises dissolve along with the alternation of generations.     

Measuring agreement between two statistics with applications to age standardization

Summary.  We detail a general method for measuring agreement between two statistics. An application is two ratios of directly standardized rates which differ only by the choice of the standard. If the statistics have a high value for the coefficient of agreement then the expected squared difference between the statistics is small relative to the variance of the average of the two statistics, and inferences vary little by changing statistics. The estimation of a coefficient of agreement between two statistics is not straightforward because there is only one pair of observed values, each statistic calculated from the data. We introduce estimators of the coefficient of agreement for two statistics and discuss their use, especially as applied to functions of standardized rates.     

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.