Article
Public, Environmental & Occupational Health
Stephen J. Bertke, Alexander P. Keil, Robert D. Daniels
Summary: This study focused on a cohort of boatbuilders exposed to styrene and found evidence for a potentially large healthy worker survivor bias, which accelerated time to lung cancer death. This suggests that influential studies on styrene-exposed workers may suffer from similar biases, warranting a reassessment of the evidence on the long-term health effects of styrene exposure.
AMERICAN JOURNAL OF EPIDEMIOLOGY
(2021)
Article
Public, Environmental & Occupational Health
Daniel Nevo, Shuji Ogino, Molin Wang
Summary: Molecular pathological epidemiology research explores pathogenic mechanisms and evaluates the effects of risk factors on disease incidence across different disease subtypes. By utilizing multinomial regression, the heterogeneity in exposure effects is examined, but there may be a potential selection bias leading to the inability to recover causal effects.
INTERNATIONAL JOURNAL OF EPIDEMIOLOGY
(2021)
Article
Genetics & Heredity
Yuanyuan Yu, Lei Hou, Xu Shi, Xiaoru Sun, Xinhui Liu, Yifan Yu, Zhongshang Yuan, Hongkai Li, Fuzhong Xue
Summary: In this study, the authors propose a theorem for causal effect invariance under different selection mechanisms and find that selection mechanisms in sample II have a larger influence on biases and type I error rates than those in sample I. Application demonstrates that nonrandom selection in sample II can magnify the causal effect estimation of obesity on HbA1c levels.
Article
Business, Finance
Aizhan Anarkulova, Scott Cederburg, Michael S. O'Doherty
Summary: This study looked at the distribution of long-term equity returns in 39 developed countries from 1841 to 2019, finding significant uncertainty in stock market outcomes over long periods. It estimates a 12% chance that a diversified investor will lose relative to inflation over a 30-year investment horizon, contradicting the conventional belief that stocks are safe investments over the long term.
JOURNAL OF FINANCIAL ECONOMICS
(2022)
Article
Mathematical & Computational Biology
Paul Bramley, Jose A. Lopez-Lopez, Julian P. T. Higgins
Summary: Standard meta-analysis methods are vulnerable to bias from incomplete reporting of results and poor study quality, and alternative methods do not perform well under substantial bias. Various bias-robust methods were evaluated under simulated conditions, but all showed poor performance in the presence of bias.
RESEARCH SYNTHESIS METHODS
(2021)
Article
Public, Environmental & Occupational Health
Robert M. Park
Summary: Diesel exhaust has been identified as a lung carcinogen in the latter half of the 20th century. This study explores the relationship between diesel exposure and lung cancer mortality rates. The results show that lung cancer mortality rates decrease with longer employment duration, but increase with cumulative REC and non-diesel exposures, suggesting a worker survivor effect. The study estimates the excess lifetime risks of lung cancer associated with different levels of REC exposure.
Article
Biodiversity Conservation
O. L. Pescott, P. A. Stroh, T. A. Humphrey, K. J. Walker
Summary: This article discusses the importance of temporal trends in species occupancy or abundance for ecology and conservation and proposes a simple technique that combines line ensemble approaches and discretization of probability information for clear communication of model-based uncertainty.
ECOLOGICAL INDICATORS
(2022)
Article
Multidisciplinary Sciences
Carlos Cinelli, Nathan LaPierre, Brian L. Hill, Sriram Sankararaman, Eleazar Eskin
Summary: The authors developed MR-SENSEMAKR, a software tool that quantifies the robustness of Mendelian Randomization (MR) study findings, and proposed sensitivity analysis tools to assess the validity threats to the results. They demonstrated how these tools can help researchers differentiate between robust and fragile findings using examples of the effect of body mass index on diastolic blood pressure and Townsend deprivation index.
NATURE COMMUNICATIONS
(2022)
Article
Public, Environmental & Occupational Health
Koichiro Shiba, Takuya Kawahara, Jun Aida, Katsunori Kondo, Naoki Kondo, Peter James, Mariana Arcaya, Ichiro Kawachi
Summary: The study highlights two underrecognized challenges in studying the long-term health effects of disasters among survivors, including time-varying effects of disasters on outcomes and selection bias due to attrition. Results demonstrate that ignoring these challenges may underestimate the long-term health effects of disasters.
AMERICAN JOURNAL OF EPIDEMIOLOGY
(2021)
Review
Biochemistry & Molecular Biology
Christiaan de Leeuw, Jeanne Savage, Ioan Gabriel Bucur, Tom Heskes, Danielle Posthuma
Summary: With the availability of large genetic data sets, Mendelian Randomization (MR) has become popular as a secondary analysis method. Using genetic variants as instrumental variables, MR can estimate causal effects between phenotypes when experimental research is not feasible. However, strong assumptions are required, and not meeting these assumptions can lead to biased results. Therefore, understanding and evaluating these assumptions is crucial when using MR.
EUROPEAN JOURNAL OF HUMAN GENETICS
(2022)
Article
Ecology
Johannes Oberpriller, David R. Cameron, Michael C. Dietze, Florian Hartig
Summary: Ecologists rely on complex computer simulations to forecast ecological systems, but uncertainties in model parameters and structure can lead to bias and underestimation. The article proposes a framework for robust inference and suggests solutions such as data rebalancing and bias corrections to improve model accuracy. Developing better methods for robust inference in complex computer simulations is crucial for generating reliable predictions of ecosystem responses.
Article
Biochemical Research Methods
John A. Rhodes, Hector Banos, Jonathan D. Mitchell, Elizabeth S. Allman
Summary: MSCquartets is an R package for species tree hypothesis testing, inference of species trees, and inference of species networks. It takes collections of metric or topological locus trees as input, summarizes them using quartets, and displays hypothesis test results in a simplex plot. The package implements algorithms for topological and metric species tree inference, as well as level-1 topological species network inference.
Editorial Material
Public, Environmental & Occupational Health
Natalie S. Levy, Katherine M. Keyes
Summary: The paper emphasizes the importance of theory in confounding control, specifically focusing on colliders and bias control. By utilizing directed acyclic graphs, the authors provide a unified conceptualization of bias and differentiate between different sources of bias.
AMERICAN JOURNAL OF EPIDEMIOLOGY
(2021)
Article
Statistics & Probability
Matias D. Cattaneo, Yingjie Feng, Rocio Titiunik
Summary: This study addresses the fundamental problem of uncertainty quantification in synthetic control methods by developing conditional prediction intervals with finite-sample probability guarantees. The method allows for covariate adjustment and nonstationary data. By considering two distinct sources of randomness in the SC prediction, the proposed prediction intervals are constructed taking into account the statistical uncertainty, leading to principled sensitivity analysis methods. Empirical applications and a small simulation study demonstrate the numerical performance of the proposed methodology.
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
(2021)
Article
Management
Dorit S. Hochbaum, Xu Rao, Jason Sauppe
Summary: In observational studies, comparing outcomes between treatment and control samples to estimate treatment effects can be complicated by covariate imbalance. This study presents network flow formulations to minimize imbalance on two nominal covariates, with both minimum cost and maximum flow approaches. The research provides efficient solutions for this optimization problem under different constraints and discusses the complexity of the problem for variations with different numbers of covariates.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2022)
Letter
Public, Environmental & Occupational Health
Rachael K. Ross, Alexander P. Keil, Stephen R. Cole, Jessie K. Edwards, Jeffrey S. A. Stringer
AMERICAN JOURNAL OF EPIDEMIOLOGY
(2023)
Letter
Environmental Sciences
Alexander P. Keil, Jessie P. Buckley, Katie M. O'Brien, Kelly K. Ferguson, Alexandra J. White
ENVIRONMENTAL HEALTH PERSPECTIVES
(2023)
Article
Public, Environmental & Occupational Health
Morgan Miller Richey, Yvonne Golightly, Stephen William Marshall, Wendy Novicoff, Alexander Keil, Maryalice Nocera, David B. Richardson
Summary: This study conducted in North Carolina found that older workers have a higher risk of fatal occupational injury. The research results showed that the rate of fatal occupational injury among older workers did not significantly decrease before and after the economic recession.
OCCUPATIONAL AND ENVIRONMENTAL MEDICINE
(2023)
Correction
Mathematical & Computational Biology
Alexander Breskin, Stephen R. Cole, Jessie K. Edwards, Ron Brookmeyer, Joseph J. Eron, Adimora A. Adimora
STATISTICS IN MEDICINE
(2023)
Article
Biology
Audrey Renson, Michael G. Hudgens, Alexander P. Keil, Paul N. Zivich, Allison E. Aiello
Summary: This article examines sustained interventions in public health and medicine and proposes a method for evaluating population effects. The method is validated through simulation studies and applied to estimate the effect of a stay-at-home order on all-cause mortality during the COVID-19 pandemic.
Article
Multidisciplinary Sciences
Josee M. Dussault, Chifundo Zimba, Harriet E. Akello, Melissa Stockton, Sherika N. Hill, Allison Aiello, Alexander W. Keil, Bradley Gaynes, Michael Udedi, Brian Pence
Summary: While research on mental health stigma in Malawi is lacking, studies in other contexts suggest that stigma is a barrier to mental health treatment and recovery. This study analyzed the role of treatment-related stigma in depression care in Malawi and found that high anticipated treatment stigma was associated with a lower probability of achieving depression remission at the 3-month mark.
Article
Environmental Sciences
Harry Sultan, Jessie P. Buckley, Heidi J. Kalkwarf, Kim M. Cecil, Aimin Chen, Bruce P. Lanphear, Kimberly Yolton, Joseph M. Braun
Summary: This study investigated the relationship between dietary quality and macronutrient intake with serum PFAS concentrations in US adolescents, and found that higher dietary quality and dietary fiber intake were associated with lower PFAS concentrations. These findings can inform future policies in reducing human exposure to PFAS.
ENVIRONMENTAL RESEARCH
(2023)
Article
Engineering, Environmental
Shelley H. Liu, Leah Feuerstahler, Yitong Chen, Joseph M. Braun, Jessie P. Buckley
Summary: Quantifying a person's cumulative exposure burden to per- and polyfluoroalkyl substances (PFAS) mixtures is important, but different people may be exposed to different sets of PFASs. Using a single measurement model for the entire population may not be appropriate if PFAS exposure sources systematically differ. Therefore, a customized PFAS exposure burden scoring algorithm is developed to ensure equitable comparison across population subgroups. Applying this method to real data, it is found that household income and race/ethnicity influence PFAS burden scores, and using summed PFAS concentrations masks some disparities.
ENVIRONMENTAL SCIENCE & TECHNOLOGY
(2023)
Article
Engineering, Environmental
Yun Liu, Richa Gairola, Jordan R. Kuiper, George D. Papandonatos, Karl T. Kelsey, Scott M. Langevin, Jessie P. Buckley, Aimin Chen, Bruce P. Lanphear, Kim M. Cecil, Kimberly Yolton, Joseph M. Braun
Summary: Per- and polyfluoroalkyl substance (PFAS) exposure has been linked to DNA methylation changes in neonates and adults. We previously reported that prenatal PFAS exposure may have a durable impact on DNA methylation from birth to adolescence. However, few studies have examined the association of postnatal PFAS exposure with alterations in DNA methylation.
ENVIRONMENTAL SCIENCE & TECHNOLOGY LETTERS
(2023)
Review
Public, Environmental & Occupational Health
Alexander P. Keil, Sabrina Zadrozny, Jessie K. Edwards
Summary: Multi-level models are used to model data using multiple levels of information. This review examines how multi-level models can be used for causal inference with individual level exposures. The review clarifies and synthesizes complex ideas in the literature and discusses how multi-level models can relax some identifying conditions of causal inference. However, there are gaps in the literature on causal inference with multi-level models, but some published approaches are provided for further guidance. Practical advice is given on when to use multi-level models for causal inference and how to go beyond interpreting their parameters.
CURRENT EPIDEMIOLOGY REPORTS
(2023)
Article
Chemistry, Multidisciplinary
Lydia M. Louis, Jessie P. Buckley, Jordan R. Kuiper, John D. Meeker, Nadia N. Hansel, Meredith C. McCormack, Gregory Diette, Lesliam Quiros-Alcala
Summary: This study found associations between urinary biomarkers of organophosphate esters (OPEs) and respiratory symptoms in children with asthma. Specifically, higher concentrations of di-n-butyl phosphate (DBuP) were associated with the use of rescue medication.
Article
Public, Environmental & Occupational Health
Katherine Lemasters, Paul Delamater, Lauren Brinkley-Rubinstein, Jesse K. Edwards, Whitney R. Robinson, Brian Pence
Summary: High probation rates are associated with worse community mental health, including higher rates of self-inflicted injury and suicide. The study found that rural areas with high probation rates also had higher rates of self-harm and suicide. These findings highlight the collateral consequences of probation on community mental health.
Article
Public, Environmental & Occupational Health
Tyler J. S. Smith, Alexander P. Keil, Jessie P. Buckley
Summary: This review discusses how epidemiologic studies have used observational data to estimate the effects of potential interventions on early-life environmental exposures. The findings suggest a growing interest in estimating intervention effects on early-life environmental exposures, as they are directly related to possible public health actions. Future studies can link research questions to specific hypothetical interventions to build on existing work.
CURRENT ENVIRONMENTAL HEALTH REPORTS
(2023)