Two-stage Adaptive Designs in Nonlinear Mixed Effects Models: Application to Pharmacokinetics in Children

Nonlinear mixed effects models (NLMEM) are used in pharmacokinetics to analyse concentrations of patients during drug development, particularly for pediatric studies. Approaches based on the Fisher information matrix can be used to optimize their design. Local design needs some a priori parameter values which might be difficult to guess. Therefore, two-stage adaptive designs are useful to provide some flexibility. We implemented in the R function PFIM the Fisher matrix for two-stage designs in NLMEM. We evaluated, with simulations, the impact of one-stage and two-stage designs on the precision of parameter estimation when the true and a priori parameters are different.     

Variational Bayes model averaging for graphon functions and motif frequencies inference in <Emphasis Type="Italic">W</Emphasis>-graph models

W-graph refers to a general class of random graph models that can be seen as a random graph limit. It is characterized by both its graphon function and its motif frequencies. In this paper, relying on an existing variational Bayes algorithm for the stochastic block models (SBMs) along with the corresponding weights for model averaging, we derive an estimate of the graphon function as an average of SBMs with increasing number of blocks. In the same framework, we derive the variational posterior frequency of any motif. A simulation study and an illustration on a social network complete our work.     

NISO Webinar: The Future of Integrated Library Systems: Part 1: RDA & Cataloging

Abstract

This column's offerings cover late spring through summer to fall of 2011: NISO Webinar: The Future of Integrated Library Systems: Part 1: RDA & Cataloging (May 11); American Library Association Annual Conference (June 23–28); Association of College and Research Libraries New England Serials and Electronic Resources Interest Group Summer Program: Current Trends in E-Journals (August 18); Kentucky Library Association/Kentucky School Media Association Joint Conference (September 28–October 1); American Society for Information Science and Technology Annual Meeting (October 9–12); Great Lakes E-Summit Conference (October 10–11); and Potomac Technical Processing Librarians Annual Meeting (October 21).     

Single-index modelling of conditional probabilities in two-way contingency tables

When analysing a contingency table, it is often worth relating the probabilities that a given individual falls into different cells from a set of predictors. These conditional probabilities are usually estimated using appropriate regression techniques. In particular, in this paper, a semiparametric model is developed. Essentially, it is only assumed that the effect of the vector of covariates on the probabilities can entirely be captured by a single index, which is a linear combination of the initial covariates. The estimation is then twofold: the coefficients of the linear combination and the functions linking this index to the related conditional probabilities have to be estimated. Inspired by the estimation procedures already proposed in the literature for single-index regression models, four estimators of the index coefficients are proposed and compared, from a theoretical point-of-view, but also practically, with the aid of simulations. Estimation of the link functions is also addressed.     

Generalized skew-normal models: properties and inference [Statistics 40 (2006) 495–505]

In [H.W. Gómez, H.S. Salinas and H. Bolfarine, Generalized skew-normal models: Properties and inference, Statistics 40(6) (2006), pp. 495–505] introduces a new family of asymmetric distributions that depends on two parameters called, α and β, such as for the particular case β = 0 obtained skew-normal distribution. In this note we give a corrected version for the expression that is used in calculating the moments of such distribution.     

The use of performance measurement as a basis for project control of offshore modification oil and gas projects

The methods presented in this article are based on the qualitative and quantitative analysis of close-out data drawn from a portfolio of 38 modification projects. The primary premise is that modification projects are intrinsically subject to quantity and complexity growth during the course of detailed engineering as a consequence of the indeterminate interface with the existing facility. The normative project control routines need to be supplemented by material take-offs-based weight monitoring as a basis for re-estimation and re-calibration of the project baselines as detailed engineering proceeds in order to mitigate this uncertainty as early as possible. Similarly, estimating needs to be based on norms drawn from performance measurement of modification work rather than extrapolations from greenfield projects, particularly the work performed on the platforms. This article presents a portfolio of project control methods based on the performance measurement principle covering the short term of single projects as well as the longer term multi-project perspective.     

Social support at work and its relationship to absenteeism

Abstract

In this study, the impact of psychosocial work characteristics on illness and work absenteeism has been examined. The study group consisted of 133 civil servants (33 men and 100 women) with a mean age of 43 years (range 21-65 years). Psychosocial work characteristics, social support, quality of life, work absenteeism, psychosomatic and gastrointestinal symptoms were assessed by means of questionnaires. Five different work support or functions were identified by factor analysis: appraisal support, belonging support, instrumental support, emotional support and supportive atmosphere. The analysis showed that work absenteeism was associated with lower belonging support and a less supportive atmosphere. Furthermore, psychosomatic symptoms were associated with lack of support at work, measured as belonging support, instrumental support and supportive atmosphere. Gastrointestinal symptoms were associated with lack of belonging support and lack of social integration outside work. A bad general health status was associated with lack of insrumental support. The association between work absenteeism and social support at work was confirmed in multivariate analysis with control for confounding factors. In this analysis, high work strain and low social support were associated with a lower quality of life, which in turn was associated with increased absenteeism. Although there are well-known difficulties in drawing causal conclusions from cross-sectional studies, it seems reasonable to conclude that social support at work is an important factor to take into consideration when analysing illness and absenteeism from work.     

What Makes Better Boards? A Closer Look at Diversity and Ownership

This study investigates the joint effect of corporate ownership and board of directors' diversity configurations on the success of strategic merger and acquisition (M&A) decisions. Board diversity is defined as the extent to which its demographic diversity as measured by the culture, nationality, gender and experience of its directors complements its statutory diversity. A theoretical framework linking ownership, board diversity and M&A strategic decision making is proposed and tested. Based on a sample of 289 M&A decisions undertaken by Canadian firms over the period 2000–2007, demographic diversity is found to have a clear and non‐linear effect on M&A performance while statutory diversity is of limited influence. Ownership is found to influence the effect of diversity, making the relation finer and more precise. This has practical implications. First, statutory diversity is not sufficient for well‐performing boards. Also, ownership is an important factor. The most advocated board diversity aimed at insuring the board's independence is not valid across all ownership configurations. From a public policy perspective, results provide support for the principles‐based approach in governance. Governance regimes should encourage the search for a balance between board diversity and the need for cohesion that best serves the firm's purpose and obligations.     

Explaining the Causes and Effects of Dynamic Capabilities Generation: A Multiple‐Indicator Multiple‐Cause Modelling Approach

The purpose of this paper is to develop a multiple‐indicator multiple‐cause model to explain dynamic capabilities generation. We use one of the main common effects of dynamic capabilities (operational, structural and strategic flexibility) to design a measurement tool for dynamic capabilities generation. Based on this measurement tool, we test the influence of several factors identified in the specialized literature as potential causes that trigger and promote dynamic capabilities generation. We use data from a survey of 200 CEOs of Spanish firms to test the model. The results show that only organizations whose managers have perceived a high degree of environmental dynamism have generated dynamic capabilities. The results also show that knowledge codification and technical innovation are significantly related to dynamic capabilities generation. We attempt to shed light on current theoretical debates about dynamic capabilities generation and provide a practical guide to explain the origin and results of dynamic capabilities that have been tested empirically.     

网络社区成员回应社区广告的社会性影响因素研究

在群体动力学理论和社会认同理论的基础上,分析了社会联结、群体利益规范、社会认同、群体意向等社会因素对网络社区成员广告反应的影响。然后,通过阐明社区成员回应社区广告的关键影响因素以及逻辑演化路径,提出了网络社区成员对广告产生积极反应的可能方式。最后,提炼了327份中国流行网络社区的用户资料,并以此为样本检验所提出的理论框架和研究假设,同时对网络社区广告的前景进行了深入讨论。