In early drug development, especially when studying new mechanisms of action or in new disease areas, little is known about the targeted or anticipated treatment effect or variability estimates. Adaptive designs that allow for early stopping but also use interim data to adapt the sample size have been proposed as a practical way of dealing with these uncertainties. Predictive power and conditional power are two commonly mentioned techniques that allow predictions of what will happen at the end of the trial based on the interim data. Decisions about stopping or continuing the trial can then be based on these predictions. However, unless the user of these statistics has a deep understanding of their characteristics important pitfalls may be encountered, especially with the use of predictive power. The aim of this paper is to highlight these potential pitfalls. It is critical that statisticians understand the fundamental differences between predictive power and conditional power as they can have dramatic effects on decision making at the interim stage, especially if used to re-evaluate the sample size. The use of predictive power can lead to much larger sample sizes than either conditional power or standard sample size calculations. One crucial difference is that predictive power takes account of all uncertainty, parts of which are ignored by standard sample size calculations and conditional power. By comparing the characteristics of each of these statistics we highlight important characteristics of predictive power that experimenters need to be aware of when using this approach. 相似文献
The paper uses the key role of technology as starting point in determining trade flows and international competitiveness at industry and country level as a growing number of theoretical contributions and empirical verifications have recognized over the past decade. The paper uses a set of new data on trade, production, technology and costs at industry level for a certain number of countries to relate trade performance to a set of different economic and technological factors across countries and industrial sectors since the early 1970s. A single model of trade specialization is applied to the data in order to establish the impact of innovation, costs and country specific factors to overall performance, both in the short run and the long run, via a panel data analysis. Model specification follows the cointegration approach, where a long-run cointegrating vector is estimated along with the dynamic adjustment towards long-run equilibrium. The paper presents some preliminary results, related to a certain number of different industrial sectors for the major industrialized countries. 相似文献
The Journal of Economic Inequality - This paper addresses the problem of the normative evaluation of income tax systems and income tax reforms. While most of the existing criteria, framed in the... 相似文献
Public participation in science and technology, is currently being encouraged in order to fulfil the calls for a more engaging, transparent, and ethical way of governing technoscientific innovation. Several institutional documents argue for the need to enrol non-scientists into research programs; funding schemes devoted to public engagement seem to be paving the way for new baselines for knowledge creation and innovation paths that include the contributions of citizens. Citizen Science stands out as an opportune movement to lead non-scientists to contribute to scientific research projects and technological innovation, and it has given rise to a broad debate intersecting many sociological aspects linked to participation and community empowerment. However, the participation of non-scientists in data collection, analysis, and interpretation is not totally new; yet it has not had the same value across time, nor has it always been considered desirable. Indeed, volunteers' engagement and amateurs' contributions have been regulated differently compared to the current rhetoric of participation. This paper gives an account of the evolution of participation of non-experts through the lens of Science and Technology Studies, investigating its desirability, how it is governed, and whether it matches the promises of Citizen Science practitioners. 相似文献
This paper analyses the inequality between the regions of the Organization for Economic Co-operation and Development (OECD) member countries by using stochastic multi-objective acceptability analysis and the associated multivariate Gini index. By considering a large number of possible combinations of weights, the distribution of the potential rankings for each region is used to measure multidimensional inequality both within and between countries. Our results show that beyond the expected two clubs of rich and poor countries, a third group of countries emerges that belongs neither to the top nor to the bottom of the ranking, an outcome that can be attributed to the presence of significant economic differences among regions within those countries. Most of the inequality lies between countries, but regional well-being also significantly varies within the same countries and we find an inverse U-shape connection between regional well-being and its inequality within the OECD member countries.
We provide a simple behavioral definition of ‘subjective mixture’ of acts for a large class of (not necessarily expected‐utility) preferences. Subjective mixtures enjoy the same algebraic properties as the ‘objective mixtures’ used to great advantage in the decision setting introduced by Anscombe and Aumann (1963). This makes it possible to formulate mixture‐space axioms in a fully subjective setting. For illustration, we present simple subjective axiomatizations of some models of choice under uncertainty, including Bewley's model of choice with incomplete preferences (2002). 相似文献