The robustness of the quasilikelihood estimator

The quasilikelihood estimator is widely used in data analysis where a likelihood is not available. We illustrate that with a given variance function it is not only conservative, in minimizing a maximum risk, but also robust against a possible misspecification of either the likelihood or cumulants of the model. In examples it is compared with estimators based on maximum likelihood and quadratic estimating functions.     

SPC as a tool for creating a successful business measurement framework

Many companies are trying to get to the bottom of what their main objectives are and what their business should be doing. The new Six Sigma approach concentrates on clarifying business strategy and making sure that everything relates to company objectives. It is vital to clarify each part of the business in such a way that everyone can understand the causes of variation that can lead to improvements in processes and performance. This paper describes a situation where the full implementation of SPC methodology has made possible a visual and widely appreciated summary of the performance of one important aspect of the business. The major part of the work was identifying the core objectives and deciding how to encapsulate each of them in one or more suitable measurements. The next step was to review the practicalities of obtaining the measurements and their reliability and representativeness. Finally, the measurements were presented in chart form and the more traditional steps of SPC analysis were commenced. Data from fast changing business environments are prone to many different problems, such as the short previous span of typical data, strange distributions and other uncertainties. Issues surrounding these and the eventual extraction of a meaningful set of information will be discussed in the paper. The measurement framework has proved very useful and, from an initial circulation of a handful of people, it now forms an important part of an information process that provides responsible managers with valuable control information. The measurement framework is kept fresh and vital by constant review and modifications. Improved electronic data collection and dissemination of the report has proved very important.     

From the discourse of "the other" to the other discourse: stakeholder-based models of evaluation and the human side of social welfare

Stakeholder-based evaluation models, like predecessor models, respond to issues and concerns identified as evaluation practice has matured. The characteristics of such models are outlined, and the relationships between stakeholder models, social work values, liberal political goals, and feminist theorizing are explored.     

Regulation of Jealousy Protest in the Context of Reunion Following Differential Treatment

Emotion regulation strategies and variation in their presentation were explored toward understanding infants' responses during reunion with mother (Re) following baseline mother–infant interaction (Bl) and differential treatment (DT) episodes. Correlation analyses revealed cohesion among distress and mother‐directed touch and proximity‐seeking during DT and Re, mother‐directed gaze during DT, and resistance during Re. The association between mother‐directed gaze during DT and distress during Re suggests that visual inattention during DT serves as a regulatory strategy. Overall, these linkages yield expanded understanding of jealousy protest as a constellation of responses that endures beyond the eliciting condition and includes regulatory behaviors. Cross‐context comparisons revealed that distress was lower during Re than during DT, but not as low as Bl, suggesting that DT poses challenge to interactive repair. Inquiry into individual variation revealed that distress during Re was augmented in laterborn males and with risk influences of dysregulated fear, and maternal insensitivity and hostility. Conversely, maternal depression was associated with less distress; later judgment as insecure, especially insecure‐avoidance, was associated with less mother‐directed behaviors. These findings suggest that dysregulation following DT is indicated by both resistance and passivity. In sum, the results highlight emotion regulation as a powerful framework for addressing recovery following DT.     

Qdf misclassification probabilities for known population parameters

Approximated QDF misclassification probabilities have been derived for bivariate normal populations with known parameter values. Tne effect of unequal covariances and population distance on the misclassification probabilities are examined     

On the Complex Quantification of Risk: Systems‐Based Perspective on Terrorism

This article highlights the complexity of the quantification of the multidimensional risk function, develops five systems‐based premises on quantifying the risk of terrorism to a threatened system, and advocates the quantification of vulnerability and resilience through the states of the system. The five premises are: (i) There exists interdependence between a specific threat to a system by terrorist networks and the states of the targeted system, as represented through the system's vulnerability, resilience, and criticality‐impact. (ii) A specific threat, its probability, its timing, the states of the targeted system, and the probability of consequences can be interdependent. (iii) The two questions in the risk assessment process: “What is the likelihood?” and “What are the consequences?” can be interdependent. (iv) Risk management policy options can reduce both the likelihood of a threat to a targeted system and the associated likelihood of consequences by changing the states (including both vulnerability and resilience) of the system. (v) The quantification of risk to a vulnerable system from a specific threat must be built on a systemic and repeatable modeling process, by recognizing that the states of the system constitute an essential step to construct quantitative metrics of the consequences based on intelligence gathering, expert evidence, and other qualitative information. The fact that the states of all systems are functions of time (among other variables) makes the time frame pivotal in each component of the process of risk assessment, management, and communication. Thus, risk to a system, caused by an initiating event (e.g., a threat) is a multidimensional function of the specific threat, its probability and time frame, the states of the system (representing vulnerability and resilience), and the probabilistic multidimensional consequences.     

SexEd.com: Values and norms in web‐based sexuality education

The sexual values and norms transmitted to adolescents through school‐based sexuality education programs have been noted and critiqued by an interdisciplinary pool of researchers. With the increasing availability of the Internet to many American adolescents, the opportunities it provides for discreet and independent exploration, and the virtual lack of regulation of information provided by web sites, the Internet is emerging as a unique and critical site of sexuality education. This work analyzes the values and norms transmitted to adolescents via 52 sexuality education web sites, drawing parallels to its school‐based counterpart and interrogating the reliance of all forms of sexuality education on a problem‐focused, gendered, and narrowly‐bounded discourse of adolescent sexuality.     

Diagnostic checks for discrete data regression models using posterior predictive simulations

Model checking with discrete data regressions can be difficult because the usual methods such as residual plots have complicated reference distributions that depend on the parameters in the model. Posterior predictive checks have been proposed as a Bayesian way to average the results of goodness-of-fit tests in the presence of uncertainty in estimation of the parameters. We try this approach using a variety of discrepancy variables for generalized linear models fitted to a historical data set on behavioural learning. We then discuss the general applicability of our findings in the context of a recent applied example on which we have worked. We find that the following discrepancy variables work well, in the sense of being easy to interpret and sensitive to important model failures: structured displays of the entire data set, general discrepancy variables based on plots of binned or smoothed residuals versus predictors and specific discrepancy variables created on the basis of the particular concerns arising in an application. Plots of binned residuals are especially easy to use because their predictive distributions under the model are sufficiently simple that model checks can often be made implicitly. The following discrepancy variables did not work well: scatterplots of latent residuals defined from an underlying continuous model and quantile–quantile plots of these residuals.