A small sample confidence interval for autoregressive parameters

This paper is concerned with interval estimation of an autoregressive parameter when the parameter space allows for magnitudes outside the unit interval. In this case, intervals based on the least-squares estimator tend to require a high level of numerical computation and can be unreliable for small sample sizes. Intervals based on the asymptotic distribution of instrumental variable estimators provide an alternative. If the instrument is taken to be the sign function, the interval is centered at the Cauchy estimator and a large sample interval can be created by estimating the standard error of this estimator. The interval proposed in this paper avoids estimating this standard error and results in a small sample improvement in coverage probability. In fact, small sample coverage is exact when the innovations come from a normal distribution.     

Spatial prediction of crystalline defects observed in molecular dynamic simulations of plastic damage

Molecular dynamic computer simulation is an essential tool in materials science to study atomic properties of materials in extreme environments and guide development of new materials. We propose a statistical analysis to emulate simulation output with the ultimate goal of efficiently approximating the computationally intensive simulation. We compare several spatial regression approaches including conditional autoregression (CAR), discrete wavelets transform (DWT), and principle components analysis (PCA). The methods are applied to simulation of copper atoms with twin wall and dislocation loop defects, under varying tilt tension angles. We find that CAR and DWT yield accurate results but fail to capture extreme defects, yet PCA better captures defect structure.     

Robust Methods—Some Examples of Their Use

We describe several analyses in which robustness considerations have proved relevant. These examples exhibit the importance of (a) graphic displays as aids to formulating a preliminary model; (b) summary statistics that reduce the influence of outliers, that (c) give added opportunities of detecting relationships, and (d) are not unduly sensitive to granularity in the observations; and (e) techniques that pay due attention to anomalies in the data that superficially may appear to be negligible but that can obscure important effects. Finally, we make some general comments on the advantages and disadvantages of robust methodology.     

Contextualizing LMX within the workgroup: The effects of LMX and justice on relationship quality and resource sharing among peers

While leader–member exchange (LMX) has evolved, a richer understanding continues to evade scholars due to the sustained focus on the leader–member dyad. We argue that LMX theory remains incomplete until contextual factors surrounding these pivotal relationships are accounted for including the impact of coworker exchange relationships, peer exchange, and perceptions of justice regarding individual LMX relationships. A fully crossed experimental design manipulating participant LMX and distributive justice and coworker LMX and distributive justice was employed to understand how these constructs affect coworker exchange relationships. Support was found for a causal model which specifies that justice moderates the causal relationship between LMX similarity and CWX, which subsequently leads to increased sharing of resources among coworkers. The data suggest that workgroup members are savvy to differences within individual leader–member relationships, where the sharing of resources among peers is determined by their own LMX, the LMX of their coworker and perceptions of justice of their respective LMX levels. These findings are contextualized in extant leadership research and practice.     

Markov models of mite movements

Continuous time Markov models were used to analyse data from two bioassays to investigate the influence of β-fraction, a by-product of hop processing, on the two-spotted spider mite. The models were fitted to aggregate counts of the numbers of live and dead mites on treated and untreated halves of discs cut from leaves of hop and French bean plants. Some of the rate parameters were time dependent. Although not all parameters could be estimated precisely, the analysis enabled the quantitative effects of treatment over time to be estimated with reasonable precision. The estimated treatment effects were largely insensitive to the assumed values of other parameters. The first bioassay showed a progressive initial response to increasing concentration of β-fraction, although data at the intermediate concentration appeared anomalous. The second bioassay showed similar responses on hop and French bean leaves, with a stronger repellent effect on the lower leaf surface than on the upper surface.     

Sampling issues in the administration of justice

Colin Aitken first became interested in sampling in the context of the administration of justice when the case of US versus Shonubi was brought to his attention. Shonubi was a Nigerian working in New York. He was arrested at Kennedy Airport when seen behaving in a suspicious manner in the baggage hall, having returned on a flight from Nigeria. He was found to have 103 bags of a white substance inside him, four of which were examined. The white substance was identified as heroin. Shonubi was arrested, tried and found guilty of drug smuggling. The question then arose as to the length of sentence he should be given.     

Experience-weighted Attraction Learning in Normal Form Games

In ‘experience-weighted attraction’ (EWA) learning, strategies have attractions that reflect initial predispositions, are updated based on payoff experience, and determine choice probabilities according to some rule (e.g., logit). A key feature is a parameter δ that weights the strength of hypothetical reinforcement of strategies that were not chosen according to the payoff they would have yielded, relative to reinforcement of chosen strategies according to received payoffs. The other key features are two discount rates, φ and ρ, which separately discount previous attractions, and an experience weight. EWA includes reinforcement learning and weighted fictitious play (belief learning) as special cases, and hybridizes their key elements. When δ= 0 and ρ= 0, cumulative choice reinforcement results. When δ= 1 and ρ=φ, levels of reinforcement of strategies are exactly the same as expected payoffs given weighted fictitious play beliefs. Using three sets of experimental data, parameter estimates of the model were calibrated on part of the data and used to predict a holdout sample. Estimates of δ are generally around .50, φ around .8 − 1, and ρ varies from 0 to φ. Reinforcement and belief-learning special cases are generally rejected in favor of EWA, though belief models do better in some constant-sum games. EWA is able to combine the best features of previous approaches, allowing attractions to begin and grow flexibly as choice reinforcement does, but reinforcing unchosen strategies substantially as belief-based models implicitly do.     

If it didn't exist we'd have to invent it … Further reflections on the ontological status of the state

In this brief response to Bob Jessop's probing yet sympathetic critique, I clarify further the ‘as if realist’ political ontology of the state. I suggest that critical realism's appeal to the ontological stratification of social reality and to the logic of retroduction are the principal stumbling blocks for ‘as if realists’, that the appeal to state power(s) as distinct from the state as real cannot circumvent the ‘as if realist’ ontological objection to the state as real since both remain conceptual abstractions, but that there is a natural affinity between the strategic‐relational approach developed by Jessop and others and the ‘as if realist’ ontology of the state that I here elucidate.     

Creating caring institutions for community informatics

This paper explores the potential affordances of applying a feminist ethics of care approach to community informatics practices in public internet access facilities. As feminist technology scholars have long observed, technology and technoculture are strongly encoded as masculine, privileging traits such as scientific knowledge, rationality, objectivity, and distance. These characteristics are expressed in traditional infomediary practices in a variety of ways, including notions of expertise, ways of conceptualizing technology, emphasis on skills attainment, and deficit-based models of user behavior. In contrast, ethics of care emphasizes the importance of relational and situated knowledge, pluralistic voices and experiences, and relationships bound by mutual interdependence. Traditionally, caring has been feminized and thus necessarily excluded from technoculture and relegated to invisible and unpaid labor. Caring and associated affective labor practices remain an under-examined subject in infomediary practices. Public libraries and community technology centers are logical places to explore for care work, given that they share many characteristics of the spaces where care work has historically been performed. We argue that an ethics of care framework has several possible affordances for infomediary practices in these institutions, including highlighting the gendered power dynamics that define and shape existing practices; distributing care work and making existing care work visible; and envisioning a more holistic and ethical approach to engaging diverse publics. We translate Tronto’s seven warning signs for ‘bad care’ in institutions into seven positive guidelines for providing ‘good care’ in public internet access facilities, then contextualize these for community informatics institutions and practices.