Statistical Inference for Stochastic Dominance and for the Measurement of Poverty and Inequality

We derive the asymptotic sampling distribution of various estimators frequently used to order distributions in terms of poverty, welfare, and inequality. This includes estimators of most of the poverty indices currently in use, as well as estimators of the curves used to infer stochastic dominance of any order. These curves can be used to determine whether poverty, inequality, or social welfare is greater in one distribution than in another for general classes of indices and for ranges of possible poverty lines. We also derive the sampling distribution of the maximal poverty lines up to which we may confidently assert that poverty is greater in one distribution than in another. The sampling distribution of convenient dual estimators for the measurement of poverty is also established. The statistical results are established for deterministic or stochastic poverty lines as well as for paired or independent samples of incomes. Our results are briefly illustrated using data for four countries drawn from the Luxembourg Income Study data bases.     

A computational framework for empirical Bayes inference

In empirical Bayes inference one is typically interested in sampling from the posterior distribution of a parameter with a hyper-parameter set to its maximum likelihood estimate. This is often problematic particularly when the likelihood function of the hyper-parameter is not available in closed form and the posterior distribution is intractable. Previous works have dealt with this problem using a multi-step approach based on the EM algorithm and Markov Chain Monte Carlo (MCMC). We propose a framework based on recent developments in adaptive MCMC, where this problem is addressed more efficiently using a single Monte Carlo run. We discuss the convergence of the algorithm and its connection with the EM algorithm. We apply our algorithm to the Bayesian Lasso of Park and Casella (J. Am. Stat. Assoc. 103:681–686, 2008) and on the empirical Bayes variable selection of George and Foster (J. Am. Stat. Assoc. 87:731–747, 2000).     

NUSAP Method for Evaluating the Data Quality in a Quantitative Microbial Risk Assessment Model for Salmonella in the Pork Production Chain

The numeral unit spread assessment pedigree (NUSAP) system was implemented to evaluate the quality of input parameters in a quantitative microbial risk assessment (QMRA) model for Salmonella spp. in minced pork meat. The input parameters were grouped according to four successive exposure pathways: (1) primary production (2) transport, holding, and slaughterhouse, (3) postprocessing, distribution, and storage, and (4) preparation and consumption. An inventory of 101 potential input parameters was used for building the QMRA model. The characteristics of each parameter were defined using a standardized procedure to assess (1) the source of information, (2) the sampling methodology and sample size, and (3) the distributional properties of the estimate. Each parameter was scored by a panel of experts using a pedigree matrix containing four criteria (proxy, empirical basis, method, and validation) to assess the quality, and this was graphically represented by means of kite diagrams. The parameters obtained significantly lower scores for the validation criterion as compared with the other criteria. Overall strengths of parameters related to the primary production module were significantly stronger compared to the other modules (the transport, holding, and slaughterhouse module, the processing, distribution, and storage module, and the preparation and consumption module). The pedigree assessment contributed to select 20 parameters, which were subsequently introduced in the QMRA model. The NUSAP methodology and kite diagrams are objective tools to discuss and visualize the quality of the parameters in a structured way. These two tools can be used in the selection procedure of input parameters for a QMRA, and can lead to a more transparent quality assurance in the QMRA.     

Social Economy and Home Care Services in Quebec: Co-Production or Co-Construction?

Third sector organizations have always played a significant role in the supply of home support services in Quebec, but this supply of services attained a crucial development phase in 1996, with the creation of 100 or so domestic help social economy enterprises (DHSEEs). These DHSEEs complemented the supply of public services delivered by the Quebec state, thus de facto taking part in the dynamics of co-production of services in the context of a mixed economy including the third sector. However, beyond that co-production, these enterprises also have to position themselves in a process of co-construction with the state, that is, in the joint, partnership-oriented construction of public policy, which provides the framework for their participation in services of public interest. Analysis of this public policy thus shows that the situation of DHSEEs in Quebec has swung, depending on the period, between co-production and various types of co-construction. A number of restrictive budget policies and subcontracting practices adopted by the Quebec state, along with tensions among DHSEE groups, curtailed the development of a genuine co-construction process during the 2000s.     

Definition and aggregation of a performance measurement system in three aeronautical workshops using the ECOGRAI method

The requirement for a performance measurement system is essential in order to know the status of the production system and then to improve its control. Focused on research on the control of production systems for 20 years with the development of GRAI methodology, the LAPS/GRAI of University Bordeaux 1 worked for more than 10 years on the definition and the implementation of performance indicator systems through the development of ECOGRAI method and on the aggregation of performance. This paper presents an application of the ECOGRAI method to a workshop inside an aeronautical subcontracting company close to Bordeaux. The first part of the paper will be dedicated to a short presentation of the ECOGRAI method. In particular, we will present six phases of the structured approach and the main tools which are used in the method: the GRAI grid, the coherence panel and the specification sheet and the identity card of the indicators. In the second part, we will present a test case. First, we will present the context of the test case and the objectives that we had to meet. Then we will present the models of the control system and of the physical system through the GRAI grid and actigrams. We will show how we proposed to model the global control of the company and the detailed control of each workshop. Then, we will focus particularly on the way we have identified the performance indicators, based on the objectives and decision variables of the GRAI grid. We will also show how we solved the problem of aggregation of performance in relation to the coordination of decision-making. In the third part, we will detail how we ensured that these indicators were adapted to the control of the workshop and how we ensured their consistency. Finally, we will show to what extent the implementation of the coherent performance indicator system had an impact on the organization and the running of the workshop.     

On the Discrete Version of the Aumann–Shapley Cost‐Sharing Method

Each agent in a finite set requests an integer quantity of an idiosyncratic good; the resulting total cost must be shared among the participating agents. The Aumann–Shapley prices are given by the Shapley value of the game where each unit of each good is regarded as a distinct player. The Aumann–Shapley cost‐sharing method charges to an agent the sum of the prices attached to the units she consumes. We show that this method is characterized by the two standard axioms of Additivity and Dummy, and the property of No Merging or Splitting: agents never find it profitable to split or to merge their consumptions. We offer a variant of this result using the No Reshuffling condition: the total cost share paid by a group of agents who consume perfectly substitutable goods depends only on their aggregate consumption. We extend this characterization to the case where agents are allowed to consume bundles of goods.     

Markov chain Monte Carlo algorithms with sequential proposals

We explore a general framework in Markov chain Monte Carlo (MCMC) sampling where sequential proposals are tried as a candidate for the next state of the Markov chain. This sequential-proposal framework can be applied to various existing MCMC methods, including Metropolis–Hastings algorithms using random proposals and methods that use deterministic proposals such as Hamiltonian Monte Carlo (HMC) or the bouncy particle sampler. Sequential-proposal MCMC methods construct the same Markov chains as those constructed by the delayed rejection method under certain circumstances. In the context of HMC, the sequential-proposal approach has been proposed as extra chance generalized hybrid Monte Carlo (XCGHMC). We develop two novel methods in which the trajectories leading to proposals in HMC are automatically tuned to avoid doubling back, as in the No-U-Turn sampler (NUTS). The numerical efficiency of these new methods compare favorably to the NUTS. We additionally show that the sequential-proposal bouncy particle sampler enables the constructed Markov chain to pass through regions of low target density and thus facilitates better mixing of the chain when the target density is multimodal.

     

Platon: Précurseur de la pensée démographique?

Since Malthus, several commentators have noted quantitative considerations in Plato's work, regarding him as a forerunner of demographic thinking. But how to explain several demographic contradictions between the Laws and The Republic? This paper brings out the consistency of Plato's thought, which cannot be demonstrated at a purely demographic level. His fascination for mathematics and the influence of the Pythagorician school should first be taken into account. However, the City, as an ideal concept and as a concrete social organization is the key to Plato's thought. Confronted with a basic problem of political philosophy, that of power and justice, Plato proposed to restore the harmony between the City as a political body and the individual citizens. Hence policy measures which we regard unduly as eugenic and demographic, are in fact based on a conception of man quite different from ours.     

Evaluation of Scenarios for Reducing Human Salmonellosis Through Household Consumption of Fresh Minced Pork Meat

Nontyphoidal salmonellosis is the second most frequently reported zoonotic disease in the European Union (EU) and is considered to be a major threat to human health worldwide. The most reported Salmonella serovar in the EU is S. Enteritidis, mainly associated with egg contamination, followed by S. Typhimurium, with the latter being the most predominant serovar isolated from pork. These findings suggest that reducing the Salmonella contamination in the pork production might be a good strategy to prevent and control human salmonellosis in the EU. Recently, a quantitative microbial risk assessment (QMRA) has been developed to assess the risks for human salmonellosis due to home consumption of fresh minced pork meat in Belgium.⁽ 1 ⁾ The newly developed risk model is called the METZOON model. In the current study, the METZOON model was used to evaluate the effectiveness of different hypothetical Salmonella mitigation strategies implemented at different stages of the minced pork production and consumption chain by means of a scenario analysis. To efficiently evaluate the mitigation strategies, model results were obtained by running simulations using the randomized complete block design. The effectiveness of a mitigation strategy is expressed using point and interval estimates of the effect size for dependent observations, expressed as the standardized difference in population means. The results indicate that the most effective strategies are taken during the slaughter processes of polishing, evisceration, and chilling, and during postprocessing, whereas interventions in the primary production and at the beginning of the slaughter process seem to have only a limited effect. Improving consumer awareness is found to be effective as well.     

Machine Learning Methods as a Tool for Predicting Risk of Illness Applying Next‐Generation Sequencing Data

Next‐generation sequencing (NGS) data present an untapped potential to improve microbial risk assessment (MRA) through increased specificity and redefinition of the hazard. Most of the MRA models do not account for differences in survivability and virulence among strains. The potential of machine learning algorithms for predicting the risk/health burden at the population level while inputting large and complex NGS data was explored with Listeria monocytogenes as a case study. Listeria data consisted of a percentage similarity matrix from genome assemblies of 38 and 207 strains of clinical and food origin, respectively. Basic Local Alignment (BLAST) was used to align the assemblies against a database of 136 virulence and stress resistance genes. The outcome variable was frequency of illness, which is the percentage of reported cases associated with each strain. These frequency data were discretized into seven ordinal outcome categories and used for supervised machine learning and model selection from five ensemble algorithms. There was no significant difference in accuracy between the models, and support vector machine with linear kernel was chosen for further inference (accuracy of 89% [95% CI: 68%, 97%]). The virulence genes FAM002725, FAM002728, FAM002729, InlF, InlJ, Inlk, IisY, IisD, IisX, IisH, IisB, lmo2026, and FAM003296 were important predictors of higher frequency of illness. InlF was uniquely truncated in the sequence type 121 strains. Most important risk predictor genes occurred at highest prevalence among strains from ready‐to‐eat, dairy, and composite foods. We foresee that the findings and approaches described offer the potential for rethinking the current approaches in MRA.