Convergence of Heavy-tailed Monte Carlo Markov Chain Algorithms

Abstract.  In this paper, we use recent results of Jarner & Roberts ( Ann. Appl. Probab., 12, 2002, 224) to show polynomial convergence rates of Monte Carlo Markov Chain algorithms with polynomial target distributions, in particular random-walk Metropolis algorithms, Langevin algorithms and independence samplers. We also use similar methodology to consider polynomial convergence of the Gibbs sampler on a constrained state space. The main result for the random-walk Metropolis algorithm is that heavy-tailed proposal distributions lead to higher rates of convergence and thus to qualitatively better algorithms as measured, for instance, by the existence of central limit theorems for higher moments. Thus, the paper gives for the first time a theoretical justification for the common belief that heavy-tailed proposal distributions improve convergence in the context of random-walk Metropolis algorithms. Similar results are shown to hold for Langevin algorithms and the independence sampler, while results for the mixing of Gibbs samplers on uniform distributions on constrained spaces are rather different in character.     

Paradoxes of American Individualism1

I point to contradictions in American individualism not unlike those suggested by Robin M. Williams Jr. I go on to suggest how twenty‐first‐century sociologists might better understand this aspect of American exceptionalism: not as an egoistic, asocial individualism, but as a covenantal, social voluntarism.     

Politics,Plurality and Problemsheds: A Strategic Approach for Reform of Agricultural Water Resources Management

Starting from the assessment that past efforts at reform in agricultural water management in developing countries have achieved very little, this article argues that a fundamental change is required in the approach to policy and institutional transformation if the present deadlock in the internalisation of ecological sustainability, human development/poverty alleviation and democratic governance into the ‘core business’ of water bureaucracies is to be overcome. ‘Social engineering’ approaches need to be replaced by ‘strategic action’ approaches that acknowledge the inherently political character and the plurality of actors, institutions and objectives of water management — a perspective operationalised here around the notions of ‘problemshed’ and ‘issue network’.     

Risk Factors of Sexual Harassment by Peers: A Longitudinal Investigation of African American and European American Adolescents

The present research explores risk factors for, and longitudinal associations of, sexual harassment by peers during adolescence. Eight‐hundred and seventy‐two African American and European American adolescents (65.4% African American, 51.1% females) were assessed during the summer after the eighth grade (mean age=14.2 years) and then again in the 11th grade (mean age=17.1 years). At the first assessment, adolescents were asked about their experiences with sexual harassment, their psychological reactions to sexual harassment, and also about their peer relationships, perceived pubertal timing, problem behavior, and mental health. At the second assessment, adolescents reported on their problem behavior and mental health. In general, youth who associated with peers who were involved in problem behavior were at risk for victimization. Among females, those who perceived themselves to be experiencing early pubertal development were also at risk. Additionally, for some adolescents, sexual harassment predicted later adjustment difficulties.     

How Resource Dependency Can Influence Social Resilience within a Primary Resource Industry*

Abstract Maintaining a healthy balance between human prosperity and environmental integrity is at the core of the principles of Ecological Sustainable Development. Resource‐protection policies are frequently implemented so as to regulate the balance between resource access and use, however, they can inadvertently compromise the ability of resource users to adapt and be resilient. Resource users who are especially dependent on a resource are more seriously compromised. But how do we define and measure resource dependency? And how do we assess its ability to influence social resilience? In this study, a conceptual model of resource dependency is developed in terms of: (i) occupational attachment, (ii) attachment to place, (iii) employability, (iv) family attitude to change, (v) business size, (vi) business approach, (vii) financial situation, (viii) level of specialisation, (ix) time spent harvesting, and (x) interest in and knowledge of the environment. The model of resource dependency and its effect on social resilience are (quantitatively and qualitatively) tested and explored using the commercial fishing industry in North Queensland, Australia. Results show that occupational attachment and employability were important influences as were business size and approach. Results can be used to identify vulnerability to institutional change and guide policy development processes.     

Social welfare functions that satisfy Pareto,anonymity, and neutrality,but not independence of irrelevant alternatives

In the presence of Pareto, non-dictatorship, full domain, and transitivity, an extremely weak independence condition disallows both anonymity and neutrality.