Analysis of adaptive directional stratification for the controlled estimation of rare event probabilities

In the context of structural reliability, a small probability to be assessed, a high computational time model and a relatively large input dimension are typical constraints which brought together lead to an interesting challenge. Indeed, in this framework many existing stochastic methods fail in estimating the failure probability with robustness.     

Fertility Behaviour and Wealth Situation in Nigeria: Evidence from 2013 Demographic and Health Survey

With the growing interest in evaluation of quality of life, emerging number of methods are presented. Each contribution varies depending on the matter of interest, and all of them address the issue of subjective weighting factors. The objective of this paper is to explore possibilities to enhance Better Life ranking methodology, available from the Better Life initiative website, using I-distance method. The result was twofold: firstly, we pointed out potential shortcomings of subjectively chosen weights of Better Life ranking methodology by employing our I-distance approach. Secondly, we provided detailed information on how each Better Life indicator contributes to the final position and emphasize the essential indicators in the process of ranking. We have collected the latest available data for 2014, including all 24 indicators of the Better Life composite index. After that we have compared the two ways of rankings, i.e. the I-distance ranking and the Better Life ranking, emphasizing the improvement offered by the I-distance methodology. Further, through iterative exclusion of indicators based on the level of their significance, we have reached the highest quality of the model. That model includes the following six indicators: personal earnings, water quality, life satisfaction, household net adjusted disposable income, employment rate, rooms per person. Hereby, we have compared and presented ranking changes at each iteration for the top 10 countries, which offer a level of consistency in their rank. In addition, one of the objectives is to help policymakers focus on the key indicators in order to improve the ranking of the country, showing governments and administrations which indicators are the most important to invest into. Moreover, our approach could be the foundation for impartial framework of the quality of life’s assessment, independent of subjectively formed weighting factors.     

BRINGING PERSONALIZED TIES BACK IN: Their Added Value for Biotech Entrepreneurs and Venture Capitalists Interorganizational Networks

Using a unique data set collected in France among biotech entrepreneurs and their venture capital investors (VCs), we measure the added value of personal relationships at the interorganizational level. Our analyses show that when two entrepreneurs share a personal collaboration tie or a personal friendship tie with a VC investor, the probability of having an advice tie and thus exchange tacit knowledge increases significantly. We confirm the importance of this kind of social embeddedness in the biotech industry where personalized ties––as opposed to institutional and contractual relationships––at the interorganizational level had not yet been examined systematically. Our results suggest that strategies of personalization of exchanges are vital for interorganizational learning. These strategies help entrepreneurs to access resources, participate in knowledge building, and co‐orientate activities in this sector.     

Blinking While Speaking and Talking,Hearing, and Listening: Communication or Individual Underlying Process?

Journal of Nonverbal Behavior - Why do eye-blinks activate during conversation? We manipulated informational content and communicative intent exchanged within dyads. By comparison to a silent...     

Fully exponential Laplace approximations for the joint modelling of survival and longitudinal data

Summary.  A common objective in longitudinal studies is the joint modelling of a longitudinal response with a time-to-event outcome. Random effects are typically used in the joint modelling framework to explain the interrelationships between these two processes. However, estimation in the presence of random effects involves intractable integrals requiring numerical integration. We propose a new computational approach for fitting such models that is based on the Laplace method for integrals that makes the consideration of high dimensional random-effects structures feasible. Contrary to the standard Laplace approximation, our method requires much fewer repeated measurements per individual to produce reliable results.     

A Bayesian ordinal logistic regression model to correct for interobserver measurement error in a geographical oral health study

Summary.  We present an approach for correcting for interobserver measurement error in an ordinal logistic regression model taking into account also the variability of the estimated correction terms. The different scoring behaviour of the 16 examiners complicated the identification of a geographical trend in a recent study on caries experience in Flemish children (Belgium) who were 7 years old. Since the measurement error is on the response the factor 'examiner' could be included in the regression model to correct for its confounding effect. However, controlling for examiner largely removed the geographical east–west trend. Instead, we suggest a (Bayesian) ordinal logistic model which corrects for the scoring error (compared with a gold standard) using a calibration data set. The marginal posterior distribution of the regression parameters of interest is obtained by integrating out the correction terms pertaining to the calibration data set. This is done by processing two Markov chains sequentially, whereby one Markov chain samples the correction terms. The sampled correction term is imputed in the Markov chain pertaining to the regression parameters. The model was fitted to the oral health data of the Signal–Tandmobiel^® study. A WinBUGS program was written to perform the analysis.     

WebStress: a web interface to explore a multidatabase bibliographic corpus on occupational stress

A bibliographic study on a multidisciplinary subject, such as occupational stress, requires a multidatabase query facility. Given this, we searched eight databases belonging to different fields (medicine, psychology, etc.) and from different countries. Thus, more than 26000 references on occupational stress were gathered. A bibliographic corpus of this sort is unusable because of the heterogeneous format of the records and the number of duplicate entries. Considering the limitations of commercial programs, we have developed a system, called WebStress, for reformatting the data and removing duplicates. The huge number of references and the research needs of updating and searching have necessitated the addition of several other functions to WebStress. Therefore WebStress comprises a web interface that makes it possible to search the corpus with advanced features (using clustering, a specialized thesaurus on stress and Boolean queries). In addition to the usual bibliographic queries on a specific database such as Medline, WebStress provides bibliometric analysis of the corpus, which might contribute to a detailed analysis on occupational stress in order to highlight the networks of researchers and to find the main topics studied in this area. WebStress is not yet available to researchers in general. It is being further developed, and also permission needs to be obtained from the eight commercial bibliographic databases that it consults.     

Optimal Nonparametric Estimation of First‐price Auctions

This paper proposes a general approach and a computationally convenient estimation procedure for the structural analysis of auction data. Considering first‐price sealed‐bid auction models within the independent private value paradigm, we show that the underlying distribution of bidders' private values is identified from observed bids and the number of actual bidders without any parametric assumptions. Using the theory of minimax, we establish the best rate of uniform convergence at which the latent density of private values can be estimated nonparametrically from available data. We then propose a two‐step kernel‐based estimator that converges at the optimal rate.