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.     

Likelihood Ratio Tests for Fixed Model Terms using Residual Maximum Likelihood

Likelihood ratio tests for fixed model terms are proposed for the analysis of linear mixed models when using residual maximum likelihood estimation. Bartlett-type adjustments, using an approximate decomposition of the data, are developed for the test statistics. A simulation study is used to compare properties of the test statistics proposed, with or without adjustment, with a Wald test. A proposed test statistic constructed by dropping fixed terms from the full fixed model is shown to give a better approximation to the asymptotic χ²-distribution than the Wald test for small data sets. Bartlett adjustment is shown to improve the χ²-approximation for the proposed tests substantially.     

A Sparse Implementation of the Average Information Algorithm for Factor Analytic and Reduced Rank Variance Models

Factor analytic variance models have been widely considered for the analysis of multivariate data particularly in the psychometrics area. Recently Smith, Cullis & Thompson (2001) have considered their use in the analysis of multi‐environment data arising from plant improvement programs. For these data, the size of the problem and the complexity of the variance models chosen to account for spatial heterogeneity within trials implies that standard algorithms for fitting factor analytic models can be computationally expensive. This paper presents a sparse implementation of the average information algorithm (Gilmour, Thompson & Cullis, 1995) for fitting factor analytic and reduced rank variance models.     

Sexual Abuse by Design: an examination of the issues in learning disability services

This paper is based upon ideas developed by the authors during their past 6 years work on issues of sexuality and sexual abuse in a wide variety of learning disability settings in Britain. The paper argues that some features of service design in themselves make sexual abuse more likely to occur. It suggests ways of reducing risk, which should work alongside the more usually suggested educative approaches to individuals and groups of vulnerable people.     

The NFC buy-out—A new form of industrial enterprise

When the Conservative Government's plans for floating the National Freight Company, Britain's biggest road freight business, on the Stock Exchange were delayed by economic factors, senior management in the business put together a scheme to buy NFC. In what became Britain's largest employee buy-out, with over 10,000 employees and pensioners putting up £6·187m of the purchase price, a new form of industrial enterprise was created. In this article Sir Peter Thompson, leader of the buy-out team and now Chairman of the National Freight Consortium plc, describes the background to the buy-out, the complex financial, legal and communications activities involved, and the way in which employee-involvement has become an integral part of the operation of what has proved to be a commercially successful business providing exceptional returns on investment.     

The advantages and disadvantages of different social welfare strategies

This paper presents a framework for consideration of change in or reform of social welfare systems. The author describes characteristics of the approaches to providing social welfare most commonly used in North America and western Europe. These include social insurance, employer mandates, individual mandates, voluntary arrangements (tax expenditures), means-tested programmes, and universal programmes (demogrants). He then evaluates each of the approaches in terms of its ability to achieve a set of social and economic objectives. The social protection objectives include treating people with dignity and respect, assuring complete coverage, equitably distributing costs and benefits, and operating efficiently to lower overhead. The objectives important to promoting a healthy economic environment include encouraging individual saving and work effort, fostering government fiscal responsibility, and facilitating smooth market functioning. The author concludes that there is no one correct way to organize social welfare systems, that each approach has strengths and weaknesses, and that different societies will attach different priorities to different objectives. Thus, as social goals change, we may expect that the particular mix of approaches used will also evolve and change over time.     

Hanging tongues: A sociological encounter with the assembly line

This study reflects approximately nine weeks of participant observation on an assembly line in the slaughter division of a large beef processing plant in the Midwest. Couched within a symbolic interactionist perspective, it focuses on the day-to-day activities of assembly line workers. It examines the sociological aspects of the workers' interaction on the job, how they coped with the danger, strain, and monotony of the work, and how they developed consumer spending norms which virtually trapped them in the plant. It also examines how the workers attempted to maintain their sense of self-worth despite the demeaning and dehumanizing aspects of their jobs.     

Ethnic Conflict and Healthcare: Cultural Dimensions of the Healthcare Delivery Crisis in Mostar, Bosnia-Herzegovina

The internecine conflict that erupted in Bosnia and Herzegovina in 1992 was only one episode in hundreds of years of ethnic tension that also produced culturally rich communities. The city of Mostar once known for its interethnic tolerance is now torn between Croatians and Muslims living together in what has been described as an armed truce. This is especially well demonstrated in the failure to rebuild the regional healthcare system, even as the health status of the population continues to deteriorate. Nonetheless this failure provides an opportunity to begin a dialogue that can lead to well being through both improved healthcare and enhanced civility.