Explore the vast range of titles available.

For obtaining causal inferences that are objective, and therefore have the best chance of revealing scientific truths, carefully designed and executed randomized experiments are generally considered to be the gold standard. Observational studies, in contrast, are generally fraught with problems that compromise any claim for objectivity of the resulting causal inferences. The thesis here is that observational studies have to be carefully designed to approximate randomized experiments, in particular, without examining any final outcome data. Often a candidate data set will have to be rejected as inadequate because of lack of data on key covariates, or because of lack of overlap in the distributions of key covariates between treatment and control groups, often revealed by careful propensity score analyses. Sometimes the template for the approximating randomized experiment will have to be altered, and the use of principal stratification can be helpful in doing this. These issues are discussed and illustrated using the framework of potential outcomes to define causal effects, which greatly clarifies critical issues.

Influenza A virus (IAV) is a respiratory pathogen that causes substantial morbidity and mortality during both seasonal and pandemic outbreaks. Infection outcomes in unexposed populations are affected by host genetics, but the host genetic architecture is not well understood. Here, we obtain a broad view of how heritable factors affect a mouse model of response to IAV infection using an 8 × 8 diallel of the eight inbred founder strains of the Collaborative Cross (CC). Expanding on a prior statistical framework for modeling treatment response in diallels, we explore how a range of heritable effects modify acute host response to IAV through 4 d postinfection. Heritable effects in aggregate explained ∼57% of the variance in IAV-induced weight loss. Much of this was attributable to a pattern of additive effects that became more prominent through day 4 postinfection and was consistent with previous reports of antiinfluenza myxovirus resistance 1 (Mx1) polymorphisms segregating between these strains; these additive effects largely recapitulated haplotype effects observed at the Mx1 locus in a previous study of the incipient CC, and are also replicated here in a CC recombinant intercross population. Genetic dominance of protective Mx1 haplotypes was observed to differ by subspecies of origin: relative to the domesticus null Mx1 allele, musculus acts dominantly whereas castaneus acts additively. After controlling for Mx1, heritable effects, though less distinct, accounted for ∼34% of the phenotypic variance. Implications for future mapping studies are discussed.

Time series data are a collection of chronological observations which are generated by several domains such as medical and financial fields. Over the years, different tasks such as classification, forecasting and clustering have been proposed to analyze this type of data. Time series data have been also used to study the effect of interventions overtime. Moreover, in many fields of science, learning the causal structure of dynamic systems and time series data is considered an interesting task which plays an important role in scientific discoveries. Estimating the effect of an intervention and identifying the causal relations from the data can be performed via causal inference. Existing surveys on time series discuss traditional tasks such as classification and forecasting or explain the details of the approaches proposed to solve a specific task. In this paper, we focus on two causal inference tasks, i.e., treatment effect estimation and causal discovery for time series data and provide a comprehensive review of the approaches in each task. Furthermore, we curate a list of commonly used evaluation metrics and datasets for each task and provide an in-depth insight. These metrics and datasets can serve as benchmark for research in the field.

We investigate large-sample properties of treatment effect estimators under unknown interference in randomized experiments. The inferential target is a generalization of the average treatment effect estimand that marginalizes over potential spillover effects. We show that estimators commonly used to estimate treatment effects under no interference are consistent for the generalized estimand for several common experimental designs under limited but otherwise arbitrary and unknown interference. The rates of convergence depend on the growth rate of the unit-average amount of interference and the degree to which the interference aligns with dependencies in treatment assignment. Importantly for practitioners, the results imply that even if one erroneously assumes that units do not interfere in a setting with moderate interference, standard estimators are nevertheless likely to be close to an average treatment effect if the sample is sufficiently large. Conventional confidence statements may, however, not be accurate.

In clinical trials, postrandomization events, such as treatment discontinuation or the use of rescue medication, can complicate the interpretation of results. An estimand is a precise description of the treatment effect that investigators wish to estimate. Estimands facilitate more straightforward interpretation of trial results by explicitly defining how postrandomization “intercurrent” events are incorporated into the research question. This article introduces the five key attributes of estimands (population, treatment conditions, endpoint, summary measure, and strategies for intercurrent events) and explains the five main strategies for managing intercurrent events (treatment policy, composite, while on treatment, hypothetical, and principal stratum). Using a practical example of a trial comparing cognitive behavioral therapy vs medication for mild anxiety, we demonstrate how different estimand choices lead to varying study designs, analyses, and interpretations. Understanding estimands helps researchers design better trials and enables stakeholders to determine if the results are relevant to their situation. We also explain how sensitivity analyses can be used to check the reliability of results by assessing how results change under different statistical assumptions.

[This corrects the article DOI: 10.3389/fimmu.2024.1343301.].

The notion of causality assumes a paramount position within the realm of human cognition. Over the past few decades, there has been significant advancement in the domain of causal effect estimation across various disciplines, including but not limited to computer science, medicine, economics, and industrial applications. Given the continous advancements in deep learning methodologies, there has been a notable surge in its utilization for the estimation of causal effects using counterfactual data. Typically, deep causal models map the characteristics of covariates to a representation space and then design various objective functions to estimate counterfactual data unbiasedly. Different from the existing surveys on causal models in machine learning, this review mainly focuses on the overview of the deep causal models based on neural networks, and its core contributions are as follows: (1) we cast insight on a comprehensive overview of deep causal models from both timeline of development and method classification perspectives; (2) we outline some typical applications of causal effect estimation to industry; (3) we also endeavor to present a detailed categorization and analysis on relevant datasets, source codes and experiments.

Background The 2019 coronavirus disease pandemic (COVID-19) poses an enormous threat to public health worldwide, and the ensuing management of social isolation has greatly decreased opportunities for physical activity (PA) and increased opportunities for leisure sedentary behaviors (LSB). Given that both PA and LSB have been established as major influencing factors for obesity, diabetes and cardiometabolic syndrome, whether PA/LSB in turn affects the susceptibility to COVID-19 by disrupting metabolic homeostasis remains to be explored. In this study, we aimed to systematically evaluate the causal relationship between PA/LSB and COVID-19 susceptibility, hospitalization and severity using a Mendelian randomization study. Methods Data were obtained from a large-scale PA dataset (N = 377,000), LSB dataset (N = 422,218) and COVID-19 Host Genetics Initiative (N = 2,586,691). The causal effects were estimated with inverse variance weighted, MR-Egger, weighted median and MR-PRESSO. Sensitivity analyses were implemented with Cochran’s Q test, MR-Egger intercept test, MR-PRESSO, leave-one-out analysis and the funnel plot. Risk factor analyses were further conducted to investigate the potential mediators. Results Genetically predicted accelerometer-assessed PA decreased the risk for COVID-19 hospitalization (OR = 0.93, 95% CI 0.88–0.97; P = 0.002), while leisure television watching significantly increased the risk of COVID-19 hospitalization (OR = 1.55, 95% CI 1.29–1.88; P = 4.68 × 10 –6 ) and disease severity (OR = 1.85, 95% CI 1.33–2.56; P = 0.0002) after Bonferroni correction. No causal effects of self-reported moderate to vigorous physical activity (MVPA), accelerometer fraction of accelerations > 425 milligravities, computer use or driving on COVID-19 progression were observed. Risk factor analyses indicated that the above causal associations might be mediated by several metabolic risk factors, including smoking, high body mass index, elevated serum triglyceride levels, insulin resistance and the occurrence of type 2 diabetes. Conclusion Our findings supported a causal effect of accelerometer-assessed PA on the reduced risk of COVID-19 hospitalization as well as television watching on the increased risk of COVID-19 hospitalization and severity, which was potentially mediated by smoking, obesity and type 2 diabetes-related phenotypes. Particular attention should be given to reducing leisure sedentary behaviors and encouraging proper exercise during isolation and quarantine for COVID-19.

Data collected on 2550 Kurdi lambs originated from 1505 dams and 149 sires during 1991 to 2015 in Hossein Abad Kurdi Sheep Breeding Station, located in Shirvan city, North Khorasan province, North-eastern area of Iran, were used for inferring causal relationship among the body weights at birth (BW), at weaning (WW), at six-month age (6MW), at nine-month age (9MW) and yearling age (YW). The inductive causation (IC) algorithm was employed to search for causal structure among these traits. This algorithm was applied to the posterior distribution of the residual (co)variance matrix of a standard multivariate model (SMM). The causal structure detected by the IC algorithm coupling with biological prior knowledge provides a temporal recursive causal network among the studied traits. The studied traits were analyzed under three multivariate models including SMM, fully recursive multivariate model (FRM) and IC-based multivariate model (ICM) via a Bayesian approach by 100,000 iterations, thinning interval of 10 and the first 10,000 iterations as burn-in. The three considered multivariate models (SMM, FRM and ICM) were compared using deviance information criterion (DIC) and predictive ability measures including mean square of error (MSE) and Pearson's correlation coefficient between the observed and predicted values (r(y, )) of records. In general, structural equation based models (FRM and ICM) performed better than SMM in terms of lower DIC and MSE and also higher r(y, ). Among the tested models ICM had the lowest (36678.551) and SMM had the highest (36744.107)DIC values. In each case of the traits studied, the lowest MSE and the highest r(y, ) were obtained under ICM. The causal effects of BW on WW, WW on 6MW, 6MW on 9MW and 9MW on YW were statistically significant values of 1.478, 0.737, 0.776 and 0.929 kg, respectively (99% highest posterior density intervals did not include zero).

We investigate the problem of inferring the causal predictors of a response Y from a set of d explanatory variables (X 1 , ..., X d ). Classical ordinary least-square regression includes all predictors that reduce the variance of Y. Using only the causal predictors instead leads to models that have the advantage of remaining invariant under interventions; loosely speaking they lead to invariance across different \"environments\" or \"heterogeneity patterns.\" More precisely, the conditional distribution of Y given its causal predictors is the same for all observations, provided that there are no interventions on Y. Recent work exploits such a stability to infer causal relations from data with different but known environments. We show that even without having knowledge of the environments or heterogeneity pattern, inferring causal relations is possible for time-ordered (or any other type of sequentially ordered) data. In particular, this allows detecting instantaneous causal relations in multivariate linear time series, which is usually not the case for Granger causality. Besides novel methodology, we provide statistical confidence bounds and asymptotic detection results for inferring causal predictors, and present an application to monetary policy in macroeconomics. Supplementary materials for this article are available online.