Abstract
Recent years have seen an emergence of network modeling applied to moods, attitudes, and problems in the realm of psychology. In this framework, psychological variables are understood to ...directly affect each other rather than being caused by an unobserved latent entity. In this tutorial, we introduce the reader to estimating the most popular network model for psychological data: the partial correlation network. We describe how regularization techniques can be used to efficiently estimate a parsimonious and interpretable network structure in psychological data. We show how to perform these analyses in R and demonstrate the method in an empirical example on posttraumatic stress disorder data. In addition, we discuss the effect of the hyperparameter that needs to be manually set by the researcher, how to handle non-normal data, how to determine the required sample size for a network analysis, and provide a checklist with potential solutions for problems that can arise when estimating regularized partial correlation networks.
Translational Abstract
Recent years have seen an emergence in the use of networks models in psychological research to explore relationships of variables such as emotions, symptoms, or personality items. Networks have become particularly popular in analyzing mental illnesses, as they facilitate the investigation of how individual symptoms affect one-another. This article introduces a particular type of network model: the partial correlation network, and describes how this model can be estimated using regularization techniques from statistical learning. With these techniques, a researcher can gain insight in predictive and potential causal relationships between the measured variables. The article provides a tutorial for applied researchers on how to estimate these models, how to determine the sample size needed for performing such an analysis, and how to investigate the stability of results. We also discuss a list of potential pitfalls when using this methodology.
Estimation of the epidemiological burden of carotid atherosclerosis can serve as a basis for prevention and management of cardiovascular disease. We aimed to provide the first estimation on the ...prevalence, number of cases, and risk factors for carotid atherosclerosis in the general population globally and regionally.
In this systematic review, meta-analysis, and modelling study, we searched PubMed, MEDLINE, Embase, Global Health, and China National Knowledge Infrastructure for articles published from database inception until May 7, 2019, with no language restrictions, for population-based studies that quantified prevalence of carotid atherosclerosis by means of increased carotid intima-media thickness, carotid plaque, and carotid stenosis. Studies were eligible if they included bilaterally scanned carotid arteries using ultrasonography and defined increased carotid intima-media thickness as a thickness of 1·0 mm or more, carotid plaque as a focal carotid intima-media thickness of 1·5 mm or more encroaching into the lumen or at least 0·5 mm or 50% compared with the surrounding carotid intima-media thickness values, and carotid stenosis as 50% or more stenosis. Studies were excluded if the sample was not representative of the general population. We also included studies identified in our previous systematic review and meta-analysis of the prevalence of carotid atherosclerosis in China. We estimated age-specific and sex-specific prevalences of increased carotid intima-media thickness, carotid plaque, and carotid stenosis. We used UN population data to generate the number of people affected in 2000, 2015, and 2020. We did random-effects meta-analyses to assess the effects of risk factors for increased carotid intima-media thickness and carotid plaque. We derived regional numbers of people living with increased carotid intima-media thickness and carotid plaque in 2015 using a risk factors-based model by WHO region. All analyses were done in populations aged 30–79 years due to availability of data. This systematic review and meta-analysis is registered online on PROSPERO, CRD42019134709.
We identified 8632 articles through our database search, of which 515 were eligible for full-text review, including 37 articles from our previous study, and 59 articles were eligible for inclusion in our systematic review and meta-analysis. Overall, in people aged 30–79 years in 2020, the global prevalence of increased carotid intima-media thickness is estimated to be 27·6% (95% CI 16·9–41·3), equivalent to 1066·70 million affected people and a percentage change of 57·46% from 2000; of carotid plaque is estimated to be 21·1% (13·2–31·5), equivalent to 815·76 million affected people and a percentage change of 58·97% from 2000; and carotid stenosis is estimated to be 1·5% (1·1–2·1), equivalent to 57·79 million affected people and a percentage change of 59·13% from 2000. The prevalence of increased carotid intima-media thickness, carotid plaque, and carotid stenosis increased consistently with age and was higher in men than in women. Current smoking, diabetes, and hypertension were common risk factors for increased carotid intima-media thickness and carotid plaque. In 2015, the Western Pacific region had the largest share of global cases of increased carotid intima-media thickness (317·62 million 33·36% of 952·13 million affected people) and carotid plaque (240·77 million 33·20% of 725·25 million), whereas the African region had the smallest share of cases of increased carotid intima-media thickness (59·08 million 6·21%) and the Eastern Mediterranean region had the smallest share of carotid plaque cases (44·59 million 6·15%).
A substantial global burden of carotid atherosclerosis exists. Effective strategies are needed for primary prevention and management of carotid atherosclerosis. High-quality epidemiological investigations on carotid atherosclerosis are needed to better address the global burden of carotid atherosclerosis at finer levels.
None.
Mendelian randomization (MR) is being increasingly used to strengthen causal inference in observational studies. Availability of summary data of genetic associations for a variety of phenotypes from ...large genome-wide association studies (GWAS) allows straightforward application of MR using summary data methods, typically in a two-sample design. In addition to the conventional inverse variance weighting (IVW) method, recently developed summary data MR methods, such as the MR-Egger and weighted median approaches, allow a relaxation of the instrumental variable assumptions.
Here, a new method - the mode-based estimate (MBE) - is proposed to obtain a single causal effect estimate from multiple genetic instruments. The MBE is consistent when the largest number of similar (identical in infinite samples) individual-instrument causal effect estimates comes from valid instruments, even if the majority of instruments are invalid. We evaluate the performance of the method in simulations designed to mimic the two-sample summary data setting, and demonstrate its use by investigating the causal effect of plasma lipid fractions and urate levels on coronary heart disease risk.
The MBE presented less bias and lower type-I error rates than other methods under the null in many situations. Its power to detect a causal effect was smaller compared with the IVW and weighted median methods, but was larger than that of MR-Egger regression, with sample size requirements typically smaller than those available from GWAS consortia.
The MBE relaxes the instrumental variable assumptions, and should be used in combination with other approaches in sensitivity analyses.
P values and error bars help readers infer whether a reported difference would likely recur, with the sample size n used for statistical tests representing biological replicates, independent ...measurements of the population from separate experiments. We provide examples and practical tutorials for creating figures that communicate both the cell-level variability and the experimental reproducibility.
This contribution in the "Best (but Oft-Forgotten) Practices" series considers mediation analysis. A mediator (sometimes referred to as an intermediate variable, surrogate endpoint, or intermediate ...endpoint) is a third variable that explains how or why ≥2 other variables relate in a putative causal pathway. The current article discusses mediation analysis with the ultimate intention of helping nutrition researchers to clarify the rationale for examining mediation, avoid common pitfalls when using the model, and conduct well-informed analyses that can contribute to improving causal inference in evaluations of underlying mechanisms of effects on nutrition-related behavioral and health outcomes. We give specific attention to underevaluated limitations inherent in common approaches to mediation. In addition, we discuss how to conduct a power analysis for mediation models and offer an applied example to demonstrate mediation analysis. Finally, we provide an example write-up of mediation analysis results as a model for applied researchers.
Stillbirths are a major public health issue and a sensitive marker of the quality of care around pregnancy and birth. The UN Global Strategy for Women's, Children's and Adolescents’ Health (2016–30) ...and the Every Newborn Action Plan (led by UNICEF and WHO) call for an end to preventable stillbirths. A first step to prevent stillbirths is obtaining standardised measurement of stillbirth rates across countries. We estimated stillbirth rates and their trends for 195 countries from 2000 to 2019 and assessed progress over time.
For a systematic assessment, we created a dataset of 2833 country-year datapoints from 171 countries relevant to stillbirth rates, including data from registration and health information systems, household-based surveys, and population-based studies. After data quality assessment and exclusions, we used 1531 datapoints to estimate country-specific stillbirth rates for 195 countries from 2000 to 2019 using a Bayesian hierarchical temporal sparse regression model, according to a definition of stillbirth of at least 28 weeks’ gestational age. Our model combined covariates with a temporal smoothing process such that estimates were informed by data for country-periods with high quality data, while being based on covariates for country-periods with little or no data on stillbirth rates. Bias and additional uncertainty associated with observations based on alternative stillbirth definitions and source types, and observations that were subject to non-sampling errors, were included in the model. We compared the estimated stillbirth rates and trends to previously reported mortality estimates in children younger than 5 years.
Globally in 2019, an estimated 2·0 million babies (90% uncertainty interval UI 1·9–2·2) were stillborn at 28 weeks or more of gestation, with a global stillbirth rate of 13·9 stillbirths (90% UI 13·5–15·4) per 1000 total births. Stillbirth rates in 2019 varied widely across regions, from 22·8 stillbirths (19·8–27·7) per 1000 total births in west and central Africa to 2·9 (2·7–3·0) in western Europe. After west and central Africa, eastern and southern Africa and south Asia had the second and third highest stillbirth rates in 2019. The global annual rate of reduction in stillbirth rate was estimated at 2·3% (90% UI 1·7–2·7) from 2000 to 2019, which was lower than the 2·9% (2·5–3·2) annual rate of reduction in neonatal mortality rate (for neonates aged <28 days) and the 4·3% (3·8–4·7) annual rate of reduction in mortality rate among children aged 1–59 months during the same period. Based on the lower bound of the 90% UIs, 114 countries had an estimated decrease in stillbirth rate since 2000, with four countries having a decrease of at least 50·0%, 28 having a decrease of 25·0–49·9%, 50 having a decrease of 10·0–24·9%, and 32 having a decrease of less than 10·0%. For the remaining 81 countries, we found no decrease in stillbirth rate since 2000. Of these countries, 34 were in sub-Saharan Africa, 16 were in east Asia and the Pacific, and 15 were in Latin America and the Caribbean.
Progress in reducing the rate of stillbirths has been slow compared with decreases in the mortality rate of children younger than 5 years. Accelerated improvements are most needed in the regions and countries with high stillbirth rates, particularly in sub-Saharan Africa. Future prevention of stillbirths needs increased efforts to raise public awareness, improve data collection, assess progress, and understand public health priorities locally, all of which require investment.
Bill & Melinda Gates Foundation and the UK Foreign, Commonwealth and Development Office.
Bifactor and other hierarchical models have become central to representing and explaining observations in psychopathology, health, and other areas of clinical science, as well as in the behavioral ...sciences more broadly. This prominence comes after a relatively rapid period of rediscovery, however, and certain features remain poorly understood. Here, hierarchical models are compared and contrasted with other models of superordinate structure, with a focus on implications for model comparisons and interpretation. Issues pertaining to the specification and estimation of bifactor and other hierarchical models are reviewed in exploratory as well as confirmatory modeling scenarios, as are emerging findings about model fit and selection. Bifactor and other hierarchical models provide a powerful mechanism for parsing shared and unique components of variance, but care is required in specifying and making inferences about them.
We present the analysis of the interrelation between two processes accounting for the spreading of an epidemic, and the information awareness to prevent its infection, on top of multiplex networks. ...This scenario is representative of an epidemic process spreading on a network of persistent real contacts, and a cyclic information awareness process diffusing in the network of virtual social contacts between the same individuals. The topology corresponds to a multiplex network where two diffusive processes are interacting affecting each other. The analysis using a microscopic Markov chain approach reveals the phase diagram of the incidence of the epidemics and allows us to capture the evolution of the epidemic threshold depending on the topological structure of the multiplex and the interrelation with the awareness process. Interestingly, the critical point for the onset of the epidemics has a critical value (metacritical point) defined by the awareness dynamics and the topology of the virtual network, from which the onset increases and the epidemics incidence decreases.
PDF
