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.     

Rank aggregation using latent-scale distance-based models

Rank aggregation aims at combining rankings of a set of items assigned by a sample of rankers to generate a consensus ranking. A typical solution is to adopt a distance-based approach to minimize the sum of the distances to the observed rankings. However, this simple sum may not be appropriate when the quality of rankers varies. This happens when rankers with different backgrounds may have different cognitive levels of examining the items. In this paper, we develop a new distance-based model by allowing different weights for different rankers. Under this model, the weight associated with a ranker is used to measure his/her cognitive level of ranking of the items, and these weights are unobserved and exponentially distributed. Maximum likelihood method is used for model estimation. Extensions to the cases of incomplete rankings and mixture modeling are also discussed. Empirical applications demonstrate that the proposed model produces better rank aggregation than those generated by Borda and the unweighted distance-based models.

     

Reflections of an ordinary life

Philip Anderson (not his real name) was one of thirty people who talked to Wendy Booth and Tim Booth as part of their recently published study Growing Up with Parents who have Learning Difficulties (London: Routledge, 1998). Philip's stoy illustrates many of the themes common to the experience of this group: resilience in the face of risk; the importance of family, especially grandma; social exclusion; the effects of hardship; and the enduring nature of parent-child bonds.     

Internal Migration and Urban Change in Poland

The paper investigates population change and migration over the period 1984–1994 for communes. There are important conclusions emerging from this study. The first is that we are watching now a profound change of population redistribution patterns in Poland. We observed that direct upwards hierarchical mobility has been markedly modified. The first modification is the substantial reduction of migration from rural to urban locations. There were important changes in the role of cities and towns. Largest cities, massive gainers of the seventies and eighties, have tended to lose population in the mid-nineties. It is likely that they lose population mainly to the neighbouring communes. We believe that a suburbanization process has been put into motion. Medium to large sized towns and cities, in the range between 50,000 and 500,000 as well as small, but not the smallest, towns attract substantial parts of the migration pool.     

The Elementary Forms of Place and Their Transformations: A Durkheimian Model

Due to the fragmentary nature of research findings and conceptual models, the Durkheimian legacy remains undervalued in contemporary spatial theory. The paper addresses this neglect by proposing a unified Durkheimian model of place which can be applied to case history and comparative analyses. It draws together the fragmented insights of Durkheimian theory to characterize four elementary forms of place: sacred, profane, liminal and mundane. These place/space identities are maintained and transformed through rituals and narratives which depend upon contingent human actions for their sustenance. The paper concludes with an extended case study which deploys the model to explain the changing meanings of the site of the Bastille (Paris, France) over the past two centuries.     

Using Mand Training to Establish an Echoic Repertoire in Young Children with Autism

The Analysis of Verbal Behavior - This research describes a method that initially establishes a mand repertoire as the first component in producing echoic and tact repertoires in young children...     

Identification of Standard Auction Models

This paper presents new identification results for models of first–price, second–price, ascending (English), and descending (Dutch) auctions. We consider a general specification of the latent demand and information structure, nesting both private values and common values models, and allowing correlated types as well as ex ante asymmetry. We address identification of a series of nested models and derive testable restrictions enabling discrimination between models on the basis of observed data. The simplest model—symmetric independent private values—is nonparametrically identified even if only the transaction price from each auction is observed. For richer models, identification and testable restrictions may be obtained when additional information of one or more of the following types is available: (i) the identity of the winning bidder or other bidders; (ii) one or more bids in addition to the transaction price; (iii) exogenous variation in the number of bidders; (iv) bidder–specific covariates. While many private values (PV) models are nonparametrically identified and testable with commonly available data, identification of common values (CV) models requires stringent assumptions. Nonetheless, the PV model can be tested against the CV alternative, even when neither model is identified.     

Avian population dynamics and human induced change in an urban environment

The predominantly urban boroughs of Warrington and Halton straddle the river Mersey in northwest England. Since the 1970s there has been a major change in land-use associated with both innovative town design and the decline of manufacturing and chemical industries in the boroughs. Also, co-ordinated programmes have directly addressed air and water pollution. The breeding birds of the two boroughs were surveyed in 1978–84 and 2004–06 as part of the bird atlases of Cheshire and Wirral, based on tetrads (2 × 2 km squares). We divided the breeding species into eight guilds based on broad ecological characteristics of habitat or food, omitting the generalists and colonial species, and compared the change between our two atlases in the number of occupied tetrads in Halton and Warrington and in the rest of the county. Four of our eight guilds have fared significantly better within our study area: waterbirds (24 species), those feeding on invertebrates (16 species), woodland specialists (21 species) and the two species that decorate their nests with lichens. The remaining four guilds showed no difference between Halton and Warrington and the rest of Cheshire and Wirral: raptors (5 species) have increased throughout, while breeding waders (7 species), farmland seedeaters (7 species) and aerial insectivores (5 species) have declined throughout. We interpret these results in relation to improved quality of water and air and changing patterns of land-use in the urban greenspace, especially an increase in woodland cover and connectivity.     

Income management in Australia: A critical examination of the evidence

The introduction of income management – sometimes called welfare quarantining – for subgroups of Australian income security recipients within the Northern Territory, and subsequently a number of other trial sites, has provoked considerable contention. The present study critically examined the arguments and evidence presented in favour of income management with particular reference to the guidelines, methodology and findings of official evaluations conducted by the Commonwealth Government. We identified five key issues that do not seem to be adequately addressed by official evaluations: choice and control, the quality of decision making, consultation with local community members, structural disadvantage and economic cost. We used these concepts to develop a proposed alternative model for assessing the impact of income management on local communities.