Decentralizing Risk Analysis in Large Engineered Systems: An Approach to Articulating Technical and Socioorganizational Dimensions of System Performance1

Nuclear power production in France, as the domain of one national utility and one reactor builder, has a standardized profile of technical installations, safety procedures, and personnel qualifications. Despite this relative homogeneity, discrepancies are observed from one production unit to another, notably in the area of worker-safety performance. There is a strong implication for risk analysis: varying performance cannot be attributed solely to the technical dimensions of equipment, procedures, and human skills. The authors retain as a working hypothesis that safety performance is an outcome of interactions between technical and organizational factors. Traditional risk analysis appears to be underequipped to represent such interactions. The notion of decentralized risk analysis (DRA) is introduced as a means of achieving this goal. A program of applied research carried out in a NPP facility is presented. It aims at increasing, across plant work structure, knowledge and control of these interactions specific to the given context. Systematic measurements and feedback of social representations are performed, using a three-dimensional factor space of individual and organizational values. Direct involvement of the total plant population, transfer of analytic tools, methodological continuity, interactive elaboration of data, coordination of different levels of findings with operations, follow-up and feedback of measured change, are the main features of this DRA process. In the case cited, improvement observed in safety performance parallels changes in measured social representations. The value of DRA for articulating technical and organizational dimensions of risk, and for integrating information into decision-making, is argued.     

Sur l'estimation du risque encouru en reconstruisant une forme aléatoire

The problem of estimating the risk corresponding to the reconstruction of a random pattern is reviewed. It is shown that for a particular but important model, the problem is reduced to the estimation of two parameters closely related to those appearing in a two-state Markov chain, which is of independent interest. The estimation of the Markov chain's parameters is studied from the decision-theoretic point of view. Estimators which are better than others previously considered are obtained and adapted to the estimation of the corresponding risk. Examples are are analyzed; even if a very empirical method is used to give values to the parameters of an a priorilaw, some good estimators of the risk are obtained.     

Comparison of open versus closed group interventions for sexually abused adolescent girls

A first aim of this study is to evaluate the efficacy of an open group therapy for sexually abused teenagers using a quasi-experimental pretest/posttest treatment design. A second aim was to explore whether differential gains were linked to an open versus a closed group format. Results indicate that sexually abused girls involved in an open group therapy showed significant gains relative to teenagers of the control group girls for the majority of the variables considered. Analyses contrasting the two formats of group therapy fail to identify statistical differences suggesting that both open and closed group formats are likely to be associated with the same significant gains for sexually abused teenagers.     

Profit implications of estimation methods for the allocation of marketing resources

We deal with the question whether estimating heterogeneous multiplicative sales response models without carry over effects by either ordinary least squares or Gibbs sampling makes a difference if resources (like advertising budgets, sales budgets, sales force sizes, sales calls) have to be allocated to sales units (like sales districts, customer groups, individual costumers or prospects) in a profit maximizing way and only short time series are available. To this end we generate artificial series on sales and allocations by stochastic simulation. These series are used to estimate multiplicative models whose coefficients are either specific to individual sales units or follow a hierarchical Bayesian framework. Ordinary least squares and Gibbs sampling serve as appropriate estimation methods. Performance of the two estimation methods is measured by recovery of optimal profits which are computed on the basis of the known true parameter values. We start to determine optimal allocations based on the plug-in method which uses average coefficients to determine expected profits. Gibbs sampling always leads to profits nearer to the true optima. This advantage of Gibbs sampling is especially pronounced for combinations with high average elasticity, high variation of elasticity and high number of sales units. On the other hand, differences between Gibbs sampling and OLS become smaller the more observations are available. Optimization with expected profits taking parameter uncertainty (i.e., the distribution of parameters) into account leads to higher profits than the plug-in method, but relative increases turn out to be rather small.     

Conceptualizing and Measuring Immigration Policies: A Comparative Perspective

In the last decade, researchers have developed many innovative ideas for the construction of indices measuring immigration policies. Methodological considerations have, however, been largely absent from the discussion. To close this gap, this paper investigates the characteristics of existing indices by critically comparing and discussing them. We start by providing a definition of immigration policy which may serve as a benchmark when assessing the indices. By means of the analytical framework developed by Munck and Verkuilen (2002), which we adapt and customize for our analysis, we then evaluate the conceptualization, measurement, and aggregation, as well as the empirical scope of thirteen immigration policy indices. We discuss methodological strengths and weaknesses of the indices, how these affect the research questions that can be answered and what the next steps in index building within the field of immigration policy should be.     

The Interpretation of Coefficients in Models with Qualitative Dependent Variables*

A substantial body of empirical accounting, finance, management, and marketing research utilizes single equation models with discrete dependent variables. Generally, the interpretation of the coefficients of the exogenous variables is limited to the sign and relative magnitude. This paper presents three methods of interpreting the coefficients in these models. The first method interprets the coefficients as marginal probabilities and the second method interprets the coefficients as elasticities of probability. The third method utilizes sensitivity analysis and examines the effect of hypothetical changes in exogenous variables on the probability of choice. This paper applies these methods to a published research study.     

Equilibrium Wage Dispersion with Worker and Employer Heterogeneity

We construct and estimate an equilibrium search model with on–the–job–search. Firms make take–it–or–leave–it wage offers to workers conditional on their characteristics and they can respond to the outside job offers received by their employees. Unobserved worker productive heterogeneity is introduced in the form of cross–worker differences in a “competence” parameter. On the other side of the market, firms also are heterogeneous with respect to their marginal productivity of labor. The model delivers a theory of steady–state wage dispersion driven by heterogenous worker abilities and firm productivities, as well as by matching frictions. The structural model is estimated using matched employer and employee French panel data. The exogenous distributions of worker and firm heterogeneity components are nonparametrically estimated. We use this structural estimation to provide a decomposition of cross–employee wage variance. We find that the share of the cross–sectional wage variance that is explained by person effects varies across skill groups. Specifically, this share lies close to 40% for high–skilled white collars, and quickly decreases to 0% as the observed skill level decreases. The contribution of market imperfections to wage dispersion is typically around 50%.