Recognizing Structural Nonidentifiability: When Experiments Do Not Provide Information About Important Parameters and Misleading Models Can Still Have Great Fit

In the quest to model various phenomena, the foundational importance of parameter identifiability to sound statistical modeling may be less well appreciated than goodness of fit. Identifiability concerns the quality of objective information in data to facilitate estimation of a parameter, while nonidentifiability means there are parameters in a model about which the data provide little or no information. In purely empirical models where parsimonious good fit is the chief concern, nonidentifiability (or parameter redundancy) implies overparameterization of the model. In contrast, nonidentifiability implies underinformativeness of available data in mechanistically derived models where parameters are interpreted as having strong practical meaning. This study explores illustrative examples of structural nonidentifiability and its implications using mechanistically derived models (for repeated presence/absence analyses and dose–response of Escherichia coli O157:H7 and norovirus) drawn from quantitative microbial risk assessment. Following algebraic proof of nonidentifiability in these examples, profile likelihood analysis and Bayesian Markov Chain Monte Carlo with uniform priors are illustrated as tools to help detect model parameters that are not strongly identifiable. It is shown that identifiability should be considered during experimental design and ethics approval to ensure generated data can yield strong objective information about all mechanistic parameters of interest. When Bayesian methods are applied to a nonidentifiable model, the subjective prior effectively fabricates information about any parameters about which the data carry no objective information. Finally, structural nonidentifiability can lead to spurious models that fit data well but can yield severely flawed inferences and predictions when they are interpreted or used inappropriately.     

Evaluation of Proactive and Reactive Strategies for Polio Eradication Activities in Pakistan and Afghanistan

Only Pakistan and Afghanistan reported any polio cases caused by serotype 1 wild polioviruses (WPV1s) in 2017. With the dwindling cases in both countries and pressure to finish eradication with the least possible resources, a danger exists of inappropriate prioritization of efforts between the two countries and insufficient investment in the two countries to finish the job. We used an existing differential‐equation‐based poliovirus transmission and oral poliovirus (OPV) evolution model to simulate a proactive strategy to stop transmission, and different hypothetical reactive strategies that adapt the quality of supplemental immunization activities (SIAs) in response to observed polio cases in Pakistan and Afghanistan. To account for the delay in perception and adaptation, we related the coverage of the SIAs in high‐risk, undervaccinated subpopulations to the perceived (i.e., smoothed) polio incidence. Continuation of the current frequency and quality of SIAs remains insufficient to eradicate WPV1 in Pakistan and Afghanistan. Proactive strategies that significantly improve and sustain SIA quality lead to WPV1 eradication and the prevention of circulating vaccine‐derived poliovirus (cVDPV) outbreaks. Reactive vaccination efforts that adapt moderately quickly and independently to changes in polio incidence in each country may succeed in WPV1 interruption after several cycles of outbreaks, or may interrupt WPV1 transmission in one country but subsequently import WPV1 from the other country or enable the emergence of cVDPV outbreaks. Reactive vaccination efforts that adapt independently and either more rapidly or more slowly to changes in polio incidence in each country may similarly fail to interrupt WPV1 transmission and result in oscillations of the incidence. Reactive strategies that divert resources to the country of highest priority may lead to alternating large outbreaks. Achieving WPV1 eradication and subsequent successful OPV cessation in Pakistan and Afghanistan requires proactive and sustained efforts to improve vaccination intensity in under‐vaccinated subpopulations while maintaining high population immunity elsewhere.     

Physician report cards: now and in the future

The six methods used to create physician performance reports-a less pejorative term than physician report cards-are seriously flawed. These current approaches are peer review, essay-style reports, raw data, statistical reports, outcome analysis, and aggregate variation from guidelines. We must deliver what we promise in information designed to confirm dependable practitioner performance. Otherwise, we risk confirming, instead, the public's suspicion that the emphasis in "managed care" is too much on managing profit and too little on patient care. This article explores a plan for how to proceed with evaluating physician performance.     

Social Media(tion) and the Reshaping of Public/Private Boundaries in Employment Relations

Tensions surrounding social media in the employment relationship are increasingly evident in the media, public rhetoric, and courts and employment tribunals. Yet the underlying causes and dimensions of these tensions have remained largely unexplored. This article firstly reviews the available literature addressing social media and employment, outlining three primary sources of contestation: profiling, disparaging posts and blogs, and private use of social media during work time. In each area, the key dynamics and underlying concerns of the central actors involved are identified. The article then seeks to canvas explanations for these forms of contestation associated with social media at work. It is argued that the architecture of social media disrupts traditional relations in organisational life by driving employer and employee actions that (re)shape and (re)constitute the boundaries between public and private spheres. Although employers and employees are using the same social technologies, their respective concerns about and points of entry to these technologies, in contrast to traditional manifestations of conflict and resistance, are asymmetric. The article concludes with a representational summary of the relative legitimacy of concerns for organisational actors and outlines areas for future research.     

Restaurant Revenue Management at Chevys: Determining the Best Table Mix

Revenue management has been used in a variety of industries and generally takes the form of managing demand by manipulating length of customer usage and price. Supply mix is rarely considered, although it can have considerable impact on revenue. In this research, we focused on developing an optimal supply mix, specifically on determining the supply mix that would maximize revenue. We used data from a Chevys restaurant, part of a large chain of Mexican restaurants, in conjunction with a simulation model to evaluate and enumerate all possible supply (table) mixes. Compared to the restaurant's existing table mix, the optimal mix is capable of handling a 30% increase in customer volume without increasing waiting times beyond their original levels. While our study was in a restaurant context, the results of this research are applicable to other service businesses.     

Integration Between Business Planning and Information Systems Planning: Validating a Stage Hypothesis

This paper proposes and empirically validates a stages of growth model for the evolution of Information Systems Planning (ISP). A questionnaire survey of senior IS executives is used to gather information pertaining to the stages of growth model, which includes measurement of the nature and level of integration between business planning (BP) and ISP. The del test is used to validate empirically benchmark variables for each stage of BP-ISP integration. The results support the stages of growth model of BP-ISP integration and the benchmark variables are generally found to be successful in predicting the stage of integration.     

Learning about restoration of urban ecosystems: a case study integrating public participation,stormwater management,and ecological research

Restoration of ecosystem functions in urban environments is made challenging by 1) a public that often lacks understanding of ecological principles, 2) inadequate evidence of the effectiveness of restoration practices, and 3) difficulty integrating social and biophysical factors in studies of urban ecosystems. This paper describes a case study in which potential solutions to these challenges were explored. We facilitated collaborative learning through public participation in the design and implementation of an urban riparian buffer along a headwater stream in a neighborhood park, a process that was informed by ecological research. Learning outcomes were evaluated using surveys and qualitative assessment of discussion. Results indicated that participants’ knowledge about water quality problems associated with urbanization, stormwater, and nonpoint-source pollution increased, familiarity with stormwater management practices increased, and perceptions about the importance of stream ecosystem functions changed. In-stream monitoring of sediment delivery, as well as direct measurements of buffer infiltration capacity, provided early evidence of buffer effectiveness in prevention of sediment inputs to the stream and absorption of runoff from surrounding surfaces. This study provides a useful model for integration of collaborative learning through participation, ecological restoration, and ecological research in an urban setting. Elements deemed essential to success of this model included an opportunity for dialog focused on a specific natural feature, sustained interaction between participants and researchers, opportunities for hands-on participation by urban residents, and flexibility in restoration practice installation.     

Statistical inference for vector measures of inequality and poverty

In this paper, we consider methods of inference for vector measures of inequality and poverty. These vector measures may consist of several different scalar measures of inequality or poverty in a single dimension, several scalar measures of poverty which use different poverty lines, or several scalar measures of inequality or poverty in different dimensions. Our proposed methods are illustrated with a Monte Carlo simulation and two empirical examples utilizing Canadian household data.     

Infusing research integrity principles and practices into a regional master's degree-intensive university: a case study

The need for institutions of higher education to advance research and scholarly integrity across graduate degree programs involves a strong commitment from each institution to develop a comprehensive approach for promoting responsible conduct of research (RCR). In response to this need, one master's-intensive regional university implemented a three-tier model project (focusing, developing, and evaluating/sustaining) for infusing research integrity principles and practices while promoting RCR. Components of the model and implementation strategies are presented as a case study analysis. Implications of the model for promoting the RCR are projected relative to graduate programs focused on applied research.     

Making predictions from complex longitudinal data, with application to planning monitoring intervals in a national screening programme

When biological or physiological variables change over time, we are often interested in making predictions either of future measurements or of the time taken to reach some threshold value. On the basis of longitudinal data for multiple individuals, we develop Bayesian hierarchical models for making these predictions together with their associated uncertainty. Particular aspects addressed, which include some novel components, are handling curvature in individuals' trends over time, making predictions for both underlying and measured levels, making predictions from a single baseline measurement, making predictions from a series of measurements, allowing flexibility in the error and random-effects distributions, and including covariates. In the context of data on the expansion of abdominal aortic aneurysms over time, where reaching a certain threshold leads to referral for surgery, we discuss the practical application of these models to the planning of monitoring intervals in a national screening programme. Prediction of the time to reach a threshold was too imprecise to be practically useful, and we focus instead on limiting the probability of exceeding the threshold after given time intervals. Although more complex models can be shown to fit the data better, we find that relatively simple models seem to be adequate for planning monitoring intervals.