Tolerance limits under Poisson regression based on small-sample asymptotic methodology

This article explores the calculation of tolerance limits for the Poisson regression model based on the profile likelihood methodology and small-sample asymptotic corrections to improve the coverage probability performance. The data consist of n counts, where the mean or expected rate depends upon covariates via the log regression function. This article evaluated upper tolerance limits as a function of covariates. The upper tolerance limits are obtained from upper confidence limits of the mean. To compute upper confidence limits the following methodologies were considered: likelihood based asymptotic methods, small-sample asymptotic methods to improve the likelihood based methodology, and the delta method. Two applications are discussed: one application relating to defects in semiconductor wafers due to plasma etching and the other examining the number of surface faults in upper seams of coal mines. All three methodologies are illustrated for the two applications.     

Exponentially weighted moving average charts for correlated multivariate Poisson processes

In this article, we study exponentially weighted moving average (EWMA) control schemes to monitor the multivariate Poisson distribution with a general covariance structure, so that the practitioner can simultaneously monitor multiple correlated attribute processes more effectively. The statistical performance of the charts is assessed in terms of the run length properties and compared against other mainstream attribute control schemes. The application of the proposed methods to real-life and simulated datasets is demonstrated.     

A formative evaluation of the recovery public works programme in Blantyre City,Malawi

Public works programmes (PWPs) are popular social protection instruments in the context of chronic poverty but very little has been published in the way of implementation and outcomes of these programmes. This paper presents a formative process and outcome evaluation of the recovery PWP in Blantyre City, Malawi. The evaluation used longitudinal household survey data of PWP beneficiaries, programme records and interview responses from programme staff and community leaders. Largely, the process evaluation findings showed an agreement between actual and planned activities. The outcome evaluation found indications that the PWP community assets offered some potential benefits to the communities, and that PWP wages allowed the beneficiaries to purchase some food. This however, did not translate into more meals per day, nor did the earnings prevent the decline in household assets as expected. Given a plausible PWP theory and high implementation fidelity, the PWP wage rate or number of days was either just enough to smooth participant income, or insufficient altogether, to enable achievement of more distal outcomes.     

Mitigating the Impact of Functional Dominance in Cross‐Functional Process Improvement Teams

Manufacturing process improvement teams often draw upon cross‐functional expertise. However, teams dominated by a single or few functions often do not achieve the desired interdisciplinary learning and cooperation, which in turn could negatively affect the performance of that cross‐functional team. Through an empirical analysis of 149 manufacturing process improvement teams in six SIC industrial categories, we show that even after controlling for several factors such as team size, number of functions, gender diversity, ethnicity, number of management levels, and geographic dispersion of team members, psychological safety of work environment fully mediates the relationship between functional dominance and team performance. We also confirm that a team leader possessing high interpersonal justice mitigates the deficiency of dominated teams and improves team performance by fostering a psychologically safe work environment. Our recommendation therefore is that when a dominated team is unavoidable due to the needed skill sets or other organizational considerations, to ensure success it is imperative that the firm chooses a team leader who can promote psychological safety by being just, and who can effectively encourage input from all functional team members and give them objective feedback.     

Breastfeeding interventions in Kansas: A qualitative process evaluation of program goals and objectives

Across the state of Kansas, eighteen public health departments received funding through the 2011 Breastfeeding Grant Initiative to start a breastfeeding intervention. The main objective of this study was to evaluate the progress toward program goals and objectives. This study was a process evaluation. Qualitative data were collected from recipient health departments at two time-points during the program year. Structured, open-ended questions were asked through telephone interviews. This study examined: (1) progress toward program goals and objectives, (2) problems encountered during implementation, and (3) evaluation measures employed to assess program impact. All health departments reported making significant progress toward program goals and objectives and reported successful collaboration with other healthcare providers. The use of breast pumps, educational classes, and professional training of staff were reported as providing the best outcome in the promotion of breastfeeding. The majority of respondents did not measure program impact. From a public health perspective, it is important that infants receive breast milk for the first six months of life. It appears that goals and objectives set a priori guided health departments with the administration of their breastfeeding program. Results may be used to enhance and sustain delivery of breastfeeding support programs in Kansas communities.     

Process evaluation of an environmental walking and healthy eating pilot in small rural worksites

Small Steps are Easier Together (SS) was a pilot environmental intervention in small rural worksites in Upstate New York in collaboration with Extension educators. Worksite leaders teamed with co-workers to select and implement environmental changes to increase walking steps over individual baseline and to choose healthy eating options over 10 weeks. Participants were 226 primarily white, women employees in 5 sites. A mixed methods process evaluation, conducted to identify determinants of intervention effectiveness and to explain differences in outcomes across worksites, included surveys, self-reports of walking and eating, interviews, focus groups, and an intervention log. The evaluation assessed reach, characteristics of recruited participants, dose delivered, dose received, and context and compared sites on walking and eating outcomes. Emergent elements of participant-reported dose received included: active leadership, visible environmental changes, critical mass of participants, public display of accomplishments, accountability to co-workers, and group decision making. Participants at sites with high reach and dose were significantly more likely than sites with low reach and dose to achieve intervention goals. Although this small pilot needs replication, these findings describe how these evaluation methods can be applied and analyzed in an environmental intervention and provide information on trends in the data.     

Expanding and Diversifying South Mediterranean Exports through Trade Facilitation

This article explores whether trade facilitation – i.e. improved and simplified trade procedures – could be an important part of the reform agenda of the Barcelona Process. Adopting a Southern perspective by focusing on exports to the European Union (EU) from non‐EU Mediterranean countries, it tests whether the efficiency of trade procedures affects (i) bilateral volumes of exports and (ii) the number of products exported. The findings suggest that trade facilitation could lead to substantially increased export volumes and export diversification.     

Asymptotic distribution of regression correlation coefficient for Poisson regression model

This study treats an asymptotic distribution for measures of predictive power for generalized linear models (GLMs). We focus on the regression correlation coefficient (RCC) that is one of the measures of predictive power. The RCC, proposed by Zheng and Agresti is a population value and a generalization of the population value for the coefficient of determination. Therefore, the RCC is easy to interpret and familiar. Recently, Takahashi and Kurosawa provided an explicit form of the RCC and proposed a new RCC estimator for a Poisson regression model. They also showed the validity of the new estimator compared with other estimators. This study discusses the new statistical properties of the RCC for the Poisson regression model. Furthermore, we show an asymptotic normality of the RCC estimator.     

QMRA for Drinking Water: 2. The Effect of Pathogen Clustering in Single‐Hit Dose‐Response Models

Spatial and/or temporal clustering of pathogens will invalidate the commonly used assumption of Poisson‐distributed pathogen counts (doses) in quantitative microbial risk assessment. In this work, the theoretically predicted effect of spatial clustering in conventional “single‐hit” dose‐response models is investigated by employing the stuttering Poisson distribution, a very general family of count distributions that naturally models pathogen clustering and contains the Poisson and negative binomial distributions as special cases. The analysis is facilitated by formulating the dose‐response models in terms of probability generating functions. It is shown formally that the theoretical single‐hit risk obtained with a stuttering Poisson distribution is lower than that obtained with a Poisson distribution, assuming identical mean doses. A similar result holds for mixed Poisson distributions. Numerical examples indicate that the theoretical single‐hit risk is fairly insensitive to moderate clustering, though the effect tends to be more pronounced for low mean doses. Furthermore, using Jensen's inequality, an upper bound on risk is derived that tends to better approximate the exact theoretical single‐hit risk for highly overdispersed dose distributions. The bound holds with any dose distribution (characterized by its mean and zero inflation index) and any conditional dose‐response model that is concave in the dose variable. Its application is exemplified with published data from Norovirus feeding trials, for which some of the administered doses were prepared from an inoculum of aggregated viruses. The potential implications of clustering for dose‐response assessment as well as practical risk characterization are discussed.