Partially hidden multi-state modelling of a prolonged disease state defined by a composite outcome

Lifetime Data Analysis - For rheumatic diseases, Minimal Disease Activity (MDA) is usually defined as a composite outcome which is a function of several individual outcomes describing symptoms or...     

Horizontal synthetic estimation: a strategy for estimating small area health related characteristics

It would be difficult to overestimate the general importance of relevant, detailed and timely small area data for health planning and research. However, the requisites of relevance, detail and timeliness are difficult — in some cases impossible — to satisfy. In the following discussion we sketch an approach for providing small area data useful for health planners. At this time our major concern is a comprehensive approach to estimates for small areas. The particular models and estimation procedures which we will present are adopted primarily for their heuristic value. They provide a convenient and not overly complex means of discussing important aspects of a comprehensive approach to small area estimation. Our objective is to delineate in a constructive fashion the broad parameters of a comprehensive approach to the estimation of health related small area data.     

Bayesian Representation of Stochastic Processes under Learning: de Finetti Revisited

A probability distribution governing the evolution of a stochastic process has infinitely many Bayesian representations of the form μ=∫μdλ(θ). Among these, a natural representation is one whose components ( μ's) are ‘learnable’ (one can approximate μ by conditioning μ on observation of the process) and ‘sufficient for prediction’ (μ's predictions are not aided by conditioning on observation of the process). We show the existence and uniqueness of such a representation under a suitable asymptotic mixing condition on the process. This representation can be obtained by conditioning on the tail-field of the process, and any learnable representation that is sufficient for prediction is asymptotically like the tail-field representation. This result is related to the celebrated de Finetti theorem, but with exchangeability weakened to an asymptotic mixing condition, and with his conclusion of a decomposition into i.i.d. component distributions weakened to components that are learnable and sufficient for prediction.     

EXPOsing Men's Gender Role Attitudes as Porn Superfans

Much contemporary debate about pornography centers on its role in portraying and perpetuating gender inequality. This article compares traditional gendered attitudes between cisgender men attending the Adult Entertainment Expo (n = 294) and a random sample of male respondents from the 2016 General Social Survey (GSS), a U.S. representative survey of general attitudes and beliefs collected every two years (n = 863). Our survey borrowed questions from the GSS to measure attitudes about gender equality across four dimensions: (1) working mothers, (2) women in politics, (3) traditional gender roles in the family, and (4) affirmative action for women in the workplace. Through bivariate analyses, we found that “porn superfans” are no more sexist or misogynistic than the general U.S. public on two of the four measures (women in politics and women in the general workplace) and held more progressive gender‐role attitudes than the general public on the other two measures. We conducted binary logistic regressions for those two measures to determine if the relationship remained significant when controlling for other factors. For one dimension, working mothers, it did (p < .001). Our results call into question some of the claims that porn consumption fosters de facto negative and hostile attitudes toward women.