The Access/Impact Problem and the Green and Gold Roads to Open Access: An Update

The research access/impact problem arises because journal articles are not accessible to all of their would-be users; hence, they are losing potential research impact. The solution is to make all articles open access (OA, i.e., accessible online, free for all). OA articles have significantly higher citation impact than non-OA articles. There are two roads to OA: the “golden” road (publish your article in an OA journal) and the “green” road (publish your article in a non-OA journal but also self-archive it in an OA archive). About 10% of journals are gold, but over 90% are already green (i.e., they have given their authors the green light to self-archive); yet only about 10–20% of articles have been self-archived. To reach 100% OA, self-archiving needs to be mandated by researchers’ employers and funders, as they are now increasingly beginning to do.     

Stylometric analyses using Dirichlet process mixture models

Stylometry refers to the statistical analysis of literary style of authors based on the characteristics of expression in their writings. We propose an approach to stylometry based on a Bayesian Dirichlet process mixture model using multinomial word frequency data. The parameters of the multinomial distribution of word frequency data are the “word prints” of the author. Our approach is based on model-based clustering of the vectors of probability values of the multinomial distribution. The resultant clusters identify different writing styles that assist in author attribution for disputed works in a corpus. As a test case, the methodology is applied to the problem of authorship attribution involving the Federalist papers. Our results are consistent with previous stylometric analyses of these papers.     

Longitudinal Pathways between Maternal Mental Health in Infancy and Offspring Romantic Relationships in Adulthood: A 30‐year Prospective Study

Longitudinal pathways between maternal mental health in infancy and offspring romantic relationship outcomes in adulthood were examined using a 30‐year prospective longitudinal study of 196 mothers and their children. Structural equation modeling revealed that maternal mental health at 30 months was related to offspring relationship status and relationship attachment insecurity at 30 years. The adolescent variables of offspring mental health and parental relationship status mediated the link between maternal mental health and offspring relationship status. In addition, adolescent mental health and family conflict mediated the pathway between maternal mental health and offspring attachment insecurity. These results highlight the importance of individual and parental mental health to romantic relationship outcomes, and emphasize the value of taking a developmental approach to the study of romantic relationships.     

Power at a distance: Organizational power across boundaries

Organizational approaches can help to make sense of social phenomena, including inequality, politics, and culture. This is partly because large organizations exercise great power, both over employees and in their external environments. Revising Charles Perrow's classic account of the “society of organizations” in the 20th century, we argue that the organizational landscape has changed. There has been a dis‐embedding of individuals from organizations that contrasts with Perrow's idea of individuals being “absorbed” by organizations. Despite this hollowing out, there is a persistence of concentrated economic power or “concentration without centralization.” Organizational power in this landscape is increasingly exercised at a distance, not only geographically but also in the sense of moving across organizational boundaries and through technologies of valuation. Three bodies of research exemplify different types of power at a distance. (a) Research on global production networks shows how power travels across geographic and network distances. (b) Research on financialization and its consequences shows how power is mediated by frames and metrics. (c) Emerging research on big data and Artificial Intelligence shows how power is encoded into seemingly neutral technologies and made to seem inevitable. This work helps to update the sociology of organizations and opens up new research questions.     

Reference‐based sensitivity analysis for time‐to‐event data

The analysis of time‐to‐event data typically makes the censoring at random assumption, ie, that—conditional on covariates in the model—the distribution of event times is the same, whether they are observed or unobserved (ie, right censored). When patients who remain in follow‐up stay on their assigned treatment, then analysis under this assumption broadly addresses the de jure, or “while on treatment strategy” estimand. In such cases, we may well wish to explore the robustness of our inference to more pragmatic, de facto or “treatment policy strategy,” assumptions about the behaviour of patients post‐censoring. This is particularly the case when censoring occurs because patients change, or revert, to the usual (ie, reference) standard of care. Recent work has shown how such questions can be addressed for trials with continuous outcome data and longitudinal follow‐up, using reference‐based multiple imputation. For example, patients in the active arm may have their missing data imputed assuming they reverted to the control (ie, reference) intervention on withdrawal. Reference‐based imputation has two advantages: (a) it avoids the user specifying numerous parameters describing the distribution of patients' postwithdrawal data and (b) it is, to a good approximation, information anchored, so that the proportion of information lost due to missing data under the primary analysis is held constant across the sensitivity analyses. In this article, we build on recent work in the survival context, proposing a class of reference‐based assumptions appropriate for time‐to‐event data. We report a simulation study exploring the extent to which the multiple imputation estimator (using Rubin's variance formula) is information anchored in this setting and then illustrate the approach by reanalysing data from a randomized trial, which compared medical therapy with angioplasty for patients presenting with angina.     

Science for people who don't want to know about science

Newspapermen and scientists are both in pursuit of the truth. That's about all they have in common. Scientists tend to be very serious about trivial things. Journalists are often trivial about very serious things. It may not be possible to square this circle.