The R package abn is designed to fit additive Bayesian network models to observational datasets and contains routines to score Bayesian networks based on Bayesian or information theoretic formulations of generalized linear models. It is equipped with exact search and greedy search algorithms to select the best network, and supports continuous, discrete and count data in the same model and input of prior knowledge at a structural level. The Bayesian implementation supports random effects to control for one-layer clustering. In this paper, we give an overview of the methodology and illustrate the package's functionality using a veterinary dataset concerned with respiratory diseases in commercial swine production.

Objectives: We provide recent and detailed estimates of the prevalence of kinlessness (i.e., people lacking [close] kin) among older individuals in 27 countries. We add to the literature by considering a broad range of kinship ties and examining within-country variabilities by age, sex, education, and rurality of the residential area. Methods: Using data from Wave 8 (2019-2020) of the Survey of Health, Ageing, and Retirement in Europe (SHARE), we estimated the prevalence of kinlessness among individuals aged 65 and over in 26 European countries and Israel. We considered different definitions of kinlessness, from a less restrictive (based on the absence of both a partner and children) to a more restrictive one (absence of partner, children, grandchildren, parents, and siblings). Results: Kinlessness varied considerably across countries. The percentage of people aged 65 and over who lacked a partner and children ranged between 2-3.5% in the Czech Republic, Romania, Israel, and Bulgaria to more than 8% in Switzerland, Spain, Belgium, and Malta. The percentage of older people lacking all close kin considered (partner, children, grandchildren, parents, and siblings) ranged from 0.1 to 4.1%. In addition, there was substantial heterogeneity in kinlessness in some countries by age, sex, and rurality of the residential area, whereas, except for a few cases, we did not find significant differences by education. Discussion: Understanding the prevalence of kinless older adults is critical for policymakers and healthcare providers to design appropriate support systems for this potentially vulnerable group of people.

Background: Mobile health apps have the potential to motivate people to adopt healthier behavior, but many fail to maintain this behavior over time. However, it has been suggested that long-term adherence can be improved by personalizing the proposed interventions. Based on the literature, we created a conceptual framework for selecting appropriate functionalities according to the user's profile. Objective: This cross-sectional study aims to investigate if the relationships linking functionalities and profiles proposed in our conceptual framework are confirmed by user preferences. Methods: A web-based questionnaire comprising several sections was developed to determine the mobile app functionalities most likely to promote healthier behavior. First, participants completed questionnaires to define the user profile (Big Five Inventory-10, Hexad Scale, and perception of the social norm using dimensions of the Theory of Planned Behavior). Second, participants were asked to select the 5 functionalities they considered to be the most relevant to motivate healthier behavior and to evaluate them on a score ranging from 0 to 100. We will perform logistic regressions with the selected functionalities as dependent variables and with the 3 profile scales as predictors to allow us to understand the effect of the participants’ scores on each of the 3 profile scales on the 5 selected functionalities. In addition, we will perform logistic ordinal regressions with the motivation score of the functionalities chosen as dependent variables and with scores of the 3 profile scales as predictors to determine whether the scores on the different profile scales predict the functionality score. Results: Data collection was conducted between July and December 2021. Analysis of responses began in January 2022, with the publication of results expected by the end of 2022. Conclusions: This study will allow us to validate our conceptual model by defining the preferred functionalities according to user profiles. International Registered Report Identifier (IRRID): RR1-10.2196/38603

The varying-thresholds model (VTM) is a novel methodology proposed by Tutz ( Flexible predictive distributions from varying-thresholds modelling. https://doi.org/10.48550/arXiv.2103.13324, arXiv:2103.13324 2021) capable of estimating the whole conditional distribution of a response variable in a regression setting. It can be used for continuous, ordinal and count responses. In this study, conditional quantiles and prediction intervals estimated through VTM are compared with those of quantile regression. The comparison is based on a set of data-generating models to assess the performance of the two methodologies regarding the coverage and width of prediction intervals. The simulation study encompasses settings with several functional forms and types of errors. In addition, a discrete version of the continuous ranked probability score is proposed as a tool to choose the best link function for the binary models used in the fitting of VTM. In summary, the varying-thresholds model is a flexible methodology that can be broadly applied with light assumptions; it is advantageous over quantile regression when the conditional quantile function is misspecified.

In this study, dietary and serum measurements of vitamin-B6 and folate from two nested case–control studies within the European Prospective Investigation into Cancer and Nutrition study were integrated in a Bayesian framework to explore the data measurement error structure and relate dietary exposures to cancer risk. A Bayesian hierarchical model was developed, including: an exposure model, to define the unknown true intake distribution; a measurement model, to relate true intake to observed assessments; and a disease model, to estimate exposure/cancer relationships. Serum and plasma levels of vitamin-B6 and folate were inversely associated with kidney and lung cancer risk, while dietary assessments of these vitamins were not associated with kidney and lung cancer risk. The Bayesian synthesis of these data suggests a protective effect but with substantial uncertainty in the effect size.