Automating and evaluating reversible jump MCMC proposal distributions

The reversible jump Markov chain Monte Carlo (MCMC) sampler (Green in Biometrika 82:711–732, 1995) has become an invaluable device for Bayesian practitioners. However, the primary difficulty with the sampler lies with the efficient construction of transitions between competing models of possibly differing dimensionality and interpretation. We propose the use of a marginal density estimator to construct between-model proposal distributions. This provides both a step towards black-box simulation for reversible jump samplers, and a tool to examine the utility of common between-model mapping strategies. We compare the performance of our approach to well established alternatives in both time series and mixture model examples.     

Disposable waste,lands and bodies under Canada’s gendered nuclear colonialism

ABSTRACT

Nuclear colonialism, or the exploitation of Indigenous lands and peoples to sustain the nuclear fuel cycle from uranium mining and refining to nuclear energy and weapons production and the dumping of the resulting nuclear waste, occurs in many parts of the world and has generated considerable protest. This article focuses on a contemporary and ongoing case of nuclear colonialism in Canada: attempts to site two national deep geological repositories (DGRs) for nuclear waste on traditional First Nations land in Southwestern Ontario near the world’s largest operational nuclear power plant. Through histories of the rise of nuclear power and nuclear waste policy-making and their relationship to settler colonialism in Canada, as well as actions taken by the Saugeen Ojibway Nation (SON) and white settler anti-nuclear waste movements, the article explores how gender is at work in nuclear colonialism and anti-nuclear waste struggles. Gender is explored here in terms of the patriarchal nuclear imperative, the appropriation of Aboriginal land through undermining Aboriginal women’s status and the problematic relationship between First Nations and white settler women-led movements in resistance to nuclear waste burial from a feminist decolonial perspective     

Likelihood-free approximate Gibbs sampling

Likelihood-free methods such as approximate Bayesian computation (ABC) have extended the reach of statistical inference to problems with computationally intractable likelihoods. Such approaches perform well for small-to-moderate dimensional problems, but suffer a curse of dimensionality in the number of model parameters. We introduce a likelihood-free approximate Gibbs sampler that naturally circumvents the dimensionality issue by focusing on lower-dimensional conditional distributions. These distributions are estimated by flexible regression models either before the sampler is run, or adaptively during sampler implementation. As a result, and in comparison to Metropolis-Hastings-based approaches, we are able to fit substantially more challenging statistical models than would otherwise be possible. We demonstrate the sampler’s performance via two simulated examples, and a real analysis of Airbnb rental prices using a intractable high-dimensional multivariate nonlinear state-space model with a 36-dimensional latent state observed on 365 time points, which presents a real challenge to standard ABC techniques.     

Taking Feminist Violence Seriously in Feminist International Relations

In this article we explore questions about feminism and violence to constructively complicate understandings about this relationship. Feminism is conventionally positioned as oppositional to direct and structural violences, importantly so, as this has been seen key to feminism's viability as a constructive knowledge project. Yet there are increasingly persistent concerns about epistemic, juridical and other violences circulating around feminism, which render feminism's role in the production of oppositional knowledge and politics suspect. This is especially the case where western feminist ideas have been problematically taken up in neoliberal global policy making and for militarized human rights interventions. As feminist international relations scholars troubled by such associations, we investigate – via an exploration of three provocative feminist texts – how feminism is perceived to be both violated and violating by its contemporary imbrication in the violences of neoliberalism and global governance. We further suggest that metaphors of feminized corporeality, which infuse representations of feminism in these texts (especially in its western homogenized governance form), inhibit the destabilizing potential of feminism through its harmful associations with the ‘failing’ female body. This bodily shaping of feminism, which we examine by following a ‘trail of blood’, tells us something important about the relationship between feminism and violence, about recurring discursive and theoretical closures around feminism and about the possibilities for reinventions of feminism to unsettle the violent degradations, which feminists insistently reveal and decry.     

A distance-based diagnostic for trans-dimensional Markov chains

Over the last decade the use of trans-dimensional sampling algorithms has become endemic in the statistical literature. In spite of their application however, there are few reliable methods to assess whether the underlying Markov chains have reached their stationary distribution. In this article we present a distance-based method for the comparison of trans-dimensional Markov chain sample output for a broad class of models. This diagnostic will simultaneously assess deviations between and within chains. Illustration of the analysis of Markov chain sample-paths is presented in simulated examples and in two common modelling situations: a finite mixture analysis and a change-point problem.     

From humor to horror: genre and narrative purpose in abortion stories on American television

A recent increase in the number of comedic films and television programs that include abortion stories has prompted a cultural conversation about whether this is an appropriate treatment for such a topic: Can abortions be funny? Are there any genres that should not include plotlines about abortion? Indeed, most prior examinations of abortion on television have focused on dramas and their impact, without explicitly exploring the ways different genres offer a range of types of stories and creative opportunities. Using a comprehensive data-set of abortion plotlines on American television, this analysis provides a historical overview of how varying genres have addressed abortion in the past, as well as closer case studies within each of five genres: drama, soap opera, horror, science fiction, and comedy. This paper provides insight into the different narrative functions of abortion stories, with consideration of how such narratives support (in)accurate and (de)stigmatizing cultural ideas about abortion.