Inferactive data analysis

We describe inferactive data analysis, so-named to denote an interactive approach to data analysis with an emphasis on inference after data analysis. Our approach is a compromise between Tukey's exploratory and confirmatory data analysis allowing also for Bayesian data analysis. We see this as a useful step in concrete providing tools (with statistical guarantees) for current data scientists. The basis of inference we use is (a conditional approach to) selective inference, in particular its randomized form. The relevant reference distributions are constructed from what we call a DAG-DAG—a Data Analysis Generative DAG, and a selective change of variables formula is crucial to any practical implementation of inferactive data analysis via sampling these distributions. We discuss a canonical example of an incomplete cross-validation test statistic to discriminate between black box models, and a real HIV dataset example to illustrate inference after making multiple queries on data.     

Toward a Viable Progressive Third Party in 2020 and Beyond1

Creating a strong, influential third party has been an abiding aspiration on the American left, and were this goal to be achieved, it could be a great boon to subordinate groups in the United States. Yet widespread doubts persist, even among progressives that this is desirable, and especially that it is possible. Here, I briefly review compelling reasons for thinking otherwise; I then consider in some depth the potential for starting to build a viable left third party leading up to and after the pivotal 2020 election. In doing so, I go beyond the existing literature on third parties, which has yet to reflect systematically on progressive third party prospects in this period. Specifically, I assess how the emerging political environment may shape left third-party building, and I evaluate ongoing and developing attempts by key groups engaged in that effort. I find a distinct tension between conditions encouraging progressives to reform versus abandon the Democratic Party, and I identify one alternative party-building tendency that seems most able to exploit the latter impulse due to its already established electoral viability. Last, I highlight relevant questions that remain for activists hoping to create an effective national left third party.     

The red and the black: China’s social credit experiment as a total test environment

China's social credit system is an unusually explicit case where technology is used by multiple actors to turn human behavior into a test object on behalf of the state's goal of modifying the larger social environment, making it an intriguing setting for thinking about the new sociology of testing. This article considers how China's search for a usable “credit” score to both allocate financial resources and explicitly measure a citizen's trustworthiness creates an emergent experimental system of governance similar to, yet not quite captured by, the kinds of experimental processes observed in literature on the platform as a form of market-based governance. As a site where “seeing like a state” and “seeing like a market” converge, the social credit system is a vantage point for observing the changing relationship between moral and economic domains in an era of digital platforms. The article highlights the experimental quality of the system and its emerging system of governance structured around reward and punishment and argues that strategic ambiguity, institutionalized through the affordances of digital platforms, is an important part of the design of this large-scale social experiment.     

Subnational Location Capital: The Role of Subnational Institutional Actors and Socio‐spatial Factors on Firm Location

Firms do not simply locate, but rather seek to accrue location‐based advantages such as knowledge, market insidership and resource utilization. Adopting the lens of social capital, this paper explores how subnational institutional actors facilitate location capital for firms. Using qualitative case study analysis of six multinational companies (MNCs), we highlight the important role of subnational institutional actors in fostering three dimensions of subnational location capital – structural, relational and cognitive. We show that subnational location capital, defined as the economic and social assets accessible through relationships within a subnational location, enable firms to derive advantages via subnational engagement. These findings contribute to the growing literature on the dynamic interaction of firms with subnational location, particularly the nuanced role of subnational institutional actors with MNCs.     

Learning to Manage the Multirisk World

Risk assessment, perception, and management tend to focus on one risk at a time. But we live in a multirisk world. This essay in honor of the 40th anniversary of the Society for Risk Analysis (SRA) and the journal Risk Analysis suggests that we can—and have already begun to—strengthen risk analysis and policy outcomes by moving from a focus on the single to the multiple—multiple stressors, multiple impacts, and multiple decisions. This evolution can improve our abilities to assess actual risks, to confront and weigh risk-risk trade-offs and innovate risk-superior moves, and to build learning into adaptive regulation that adjusts over time. Recognizing the multirisk reality can help us understand complex systems, foresee unintended consequences, design better policy solutions, and learn to improve.     

Deepwater Horizon oil spill exposure and child health: a longitudinal analysis

Population and Environment - The BP Deepwater Horizon oil spill (DHOS) created widespread concern about threats to health among residents of the Louisiana Gulf Coast. This study uses data from the...     

A qualitative investigation of risk and protective factors for interpersonal violence in adults on the autism spectrum

Abstract

Individuals on the autism spectrum are at an increased risk of experiencing violence. This study sought to understand the opinions of adults on the spectrum regarding potential risk and protective factors for interpersonal violence. Twenty-two adults (12 men; 18 to 53 years of age) participated in semi-structured qualitative interviews. Interviews were recorded, transcribed, and analysed. The results of the qualitative analysis identified individual and contextual risk and protective factors. Protective themes focused on individual needs (awareness of the self and the environment, interpersonal knowledge/skills, skill building strategies) and supportive contexts (benefits of a trusted person, advocates, fostering acceptance and inclusion). There is a need for strategies to decrease the vulnerability to, and the impact of, interpersonal violence. Individuals on the spectrum have the capacity to provide important information regarding safety promotion and risk factors for interpersonal violence, and their expertise should play a role in guiding efforts that promote safety.     

Unclaimed Prize Information Biases Perceptions of Winning in Scratch Card Gambling

Unclaimed prize information (i.e., the number of prizes still available to be won) is information commonly provided to scratch card gamblers. However, unless the number of tickets remaining to be purchased is also provided, this information is uninformative. Despite its lack of utility in assisting gamblers in choosing the most favourable type of scratch card to play, we hypothesized that unclaimed prize information would bias participants’ judgments within a scratch card gambling context. In Experiment 1 (N?=?201), we showed that participants are influenced by this information such that they felt more likely to win, were more excited to play, and preferred to hypothetically purchase more of the scratch card with the greatest number of unclaimed prizes. In Experiment 2 (N?=?201), we attempted to ameliorate this bias by providing participants with the number of tickets remaining to be purchased and equating the payback percentages of all three games. The bias, although attenuated, still persisted in these conditions. Finally, in Experiment 3 (N?=?200), we manipulated the hypothetical scratch cards such that games with the highest number of unclaimed prizes were the least favourable, and vice versa. As in Experiment 2, participants still favoured cards with greater numbers of unclaimed prizes. Possible mechanisms underlying this bias are discussed. In conclusion, across three experiments, we demonstrate that salient unclaimed prize information is capable of exerting a strong effect over judgments related to scratch card games.