Bayesian local influence for survival models

The aim of this paper is to develop a Bayesian local influence method (Zhu et al. 2009, submitted) for assessing minor perturbations to the prior, the sampling distribution, and individual observations in survival analysis. We introduce a perturbation model to characterize simultaneous (or individual) perturbations to the data, the prior distribution, and the sampling distribution. We construct a Bayesian perturbation manifold to the perturbation model and calculate its associated geometric quantities including the metric tensor to characterize the intrinsic structure of the perturbation model (or perturbation scheme). We develop local influence measures based on several objective functions to quantify the degree of various perturbations to statistical models. We carry out several simulation studies and analyze two real data sets to illustrate our Bayesian local influence method in detecting influential observations, and for characterizing the sensitivity to the prior distribution and hazard function.     

Why a Bayesian approach to safety analysis in pharmacovigilance is important

Large databases of routinely collected data are a valuable source of information for detecting potential associations between drugs and adverse events (AE). A pharmacovigilance system starts with a scan of these databases for potential signals of drug-AE associations that will subsequently be examined by experts to aid in regulatory decision-making. The signal generation process faces some key challenges: (1) an enormous volume of drug-AE combinations need to be tested (i.e. the problem of multiple testing); (2) the results are not in a format that allows the incorporation of accumulated experience and knowledge for future signal generation; and (3) the signal generation process ignores information captured from other processes in the pharmacovigilance system and does not allow feedback. Bayesian methods have been developed for signal generation in pharmacovigilance, although the full potential of these methods has not been realised. For instance, Bayesian hierarchical models will allow the incorporation of established medical and epidemiological knowledge into the priors for each drug-AE combination. Moreover, the outputs from this analysis can be incorporated into decision-making tools to help in signal validation and posterior actions to be taken by the regulators and companies. We discuss in this paper the apparent advantage of the Bayesian methods used in safety signal generation and the similarities and differences between the two widely used Bayesian methods. We will also propose the use of Bayesian hierarchical models to address the three key challenges and discuss the reasons why Bayesian methodology still have not been fully utilised in pharmacovigilance activities.     

Statistical approaches for conducting network meta-analysis in drug development

We introduce health technology assessment and evidence synthesis briefly, and then concentrate on the statistical approaches used for conducting network meta-analysis (NMA) in the development and approval of new health technologies. NMA is an extension of standard meta-analysis where indirect as well as direct information is combined and can be seen as similar to the analysis of incomplete-block designs. We illustrate it with an example involving three treatments, using fixed-effects and random-effects models, and using frequentist and Bayesian approaches. As most statisticians in the pharmaceutical industry are familiar with SAS? software for analyzing clinical trials, we provide example code for each of the methods we illustrate. One issue that has been overlooked in the literature is the choice of constraints applied to random effects, and we show how this affects the estimates and standard errors and propose a symmetric set of constraints that is equivalent to most current practice. Finally, we discuss the role of statisticians in planning and carrying out NMAs and the strategy for dealing with important issues such as heterogeneity.     

Vendor Selection with Bundling: A Comment*

In a recent article by Rosenthal, Zydiak, and Chaudhry (1995), a mixed integer linear programming model was introduced to solve the vendor selection problem for the case in which the vendor can sell items individually or as part of a bundle. Each vendor offered only one type of bundle, and the buyer could purchase at most one bundle per vendor. The model employed n(m+ 1) binary variables, where n is the number of vendors and m is the number of products they sell. The existing model can lead to a purchasing paradox: it may force the buyer to pay more to receive less. We suggest a reformulation of the same problem that (i) eliminates this paradox and reveals a more cost-effective purchasing strategy; (ii) uses only n integer variables and significantly reduces the computational workload; and (iii) permits the buyer to purchase more than one bundle per vendor.     

Implementing integrated pest management in professional lawn care: a case study

Human choices regarding land cover management practices may influence ecosystem services provided by urban green spaces. We conducted a 2-year study to compare biological (weed, insect, and disease), aesthetic (lawn quality), and economic (lawn care program cost) attributes of an integrated pest management (IPM) program, in which pesticides are applied on the basis of treatment thresholds, with a standard program, in which pesticides are applied on a calendar basis without pest monitoring. Both programs were managed by a professional lawn care operator. Although weed incidence was low, the IPM program had significantly more lawns with weed presence than the standard program during 2005 and 2006. However, only 21% of the IPM lawns required herbicide applications in 2005, and none exceeded the treatment threshold (5% weed cover) in 2006 as compared to 100% of the standard program lawns being treated for weeds in both years. The IPM program also had significantly more lawns with insect damage than the standard program during June 2005 and August 2005, but not September 2005 and throughout 2006. Only 28% of the IPM lawns required insecticide applications in 2005 and none exceeded the threshold (5% insect damage) in 2006 whereas all of the lawns in the standard program received insecticide treatments in both years. Rhizoctonia blight was present on some of the lawns, but was not a common problem. Although lawn quality was high for both programs (>8, on a scale of 1–9), it was significantly higher for standard than for IPM program lawns during 2005, and June 2006 and September 2006, but not August 2006. The annual lawn management costs were lower for the IPM (281.50) than the standard program (281.50) than the standard program (458.06). Thirty one percent of the IPM program customers who continued with the study in 2006 did so because they were satisfied with the IPM program. Among those who did not continue with the program, 33% cited weed or insect problems, while 33% expected better results. The implications of these findings for implementation of IPM in professional lawn care are further discussed.     

邬焜和信息元哲学

在2010年8月北京举行的第四届国际信息科学基础大会上,西安交通大学的邬焜教授第一次用英文提交了将近三十年来的信息理论与哲学研究成果。其理论(信息哲学的基础理论:BTPI)聚焦于信息的自然本体论属性,以及它们对于适当理解信息的社会功能的重要性。邬教授的BTPI理论,关于需要统一诸多关键学科及其规划的新信息观,作为一种元哲学对一般信息理论(这次大会的主题)而言形成了一个主要贡献。所描述的理论能够形成一个新的跨学科范式的部分,在其中信息具有核心作用。信息元哲学的协同应用能够为解决信息领域的关键性突出问题做出贡献,并为新兴信息社会的伦理学发展提供进一步的支持。     

Firm-level correlates of emergent green supply chain management practices in the Chinese context

Greening the supply chain is increasingly a concern for many business enterprises and a challenge for logistics management in the 21st century. Of particular concern is how to arouse organizational environmental awareness and put environmental activities into practice in the logistics activities of their supply chains. This paper investigates the correlation of two major factors, organizational learning and management support, with the extent of adoption of green supply chain management (GSCM) practices in Chinese manufacturing firms, where their inbound and outbound logistics activities are potential polluters to the environment. Organizational and operational learning was derived from the firm's experience with programs such as total quality management and environmental management systems. Management support included support for GSCM ideas and practices from top and middle-level management and cooperation across organizational functions. We find significant positive relationships between organizational learning mechanisms, organizational support and the adoption of GSCM practices, after controlling for a number of other influences including regulations, marketing, supplier, cost pressures, industry levels of the relevant practice and organizational size. Implications of our findings on logistics management are discussed.