Practical considerations for sandwich variance estimation in two-stage regression settings
We present a practical approach for computing the sandwich variance estimator in two-stage regression model settings. As a motivating example for two-stage regression, we consider regression calibration, a popular approach for addressing covariate measurement error. The sandwich variance approach has been rarely applied in regression calibration, despite it requiring less computation time than popular resampling approaches for variance estimation, specifically the bootstrap. This is likely due to requiring specialized statistical coding. We first outline the steps needed to compute the sandwich variance estimator. We then ...
Source: Am J Epidemiol - November 27, 2023 Category: Epidemiology Authors: Lillian A Boe Thomas Lumley Pamela A Shaw Source Type: research
Correcting for Antibody Waning in Cumulative Incidence Estimation from Sequential Serosurveys
We present an empirically-supported approach for sero-reversion correction in cumulative incidence estimation when sequential serosurveys are conducted in the context of a newly emerging infectious disease. The correction is based on the observed dynamics of antibody titers in sero-positive cases and validated using several in silico test scenarios. Furthermore, through this approach we revise a previous cumulative incidence estimate, which relies on the assumption of an exponentially-declining probability of sero-reversion over time, of SARS-CoV-2 of 76% in Manaus, Brazil, by October 2020 to 47.6% (43.5% - 53.5%). This es...
Source: Am J Epidemiol - November 27, 2023 Category: Epidemiology Authors: Sarah Kadelka Judith A Bouman Peter Ashcroft Roland R Regoes Source Type: research
Practical considerations for sandwich variance estimation in two-stage regression settings
We present a practical approach for computing the sandwich variance estimator in two-stage regression model settings. As a motivating example for two-stage regression, we consider regression calibration, a popular approach for addressing covariate measurement error. The sandwich variance approach has been rarely applied in regression calibration, despite it requiring less computation time than popular resampling approaches for variance estimation, specifically the bootstrap. This is likely due to requiring specialized statistical coding. We first outline the steps needed to compute the sandwich variance estimator. We then ...
Source: Am J Epidemiol - November 27, 2023 Category: Epidemiology Authors: Lillian A Boe Thomas Lumley Pamela A Shaw Source Type: research
Cohort vs case-control studies on night shift work and cancer risk: the importance of exposure assessment
Am J Epidemiol. 2023 Nov 27:kwad227. doi: 10.1093/aje/kwad227. Online ahead of print.ABSTRACTIt is a general assumption that the prospective cohort design is the gold standard approach and superior to the case-control design in epidemiology. However, there may be exceptions if the exposure is complex and requires collection of detailed information on many different aspects. Night shift work is an example of such a complex occupational exposure which impairs circadian rhythms and may increase the risk of breast, prostate and colorectal cancer. So far for logistic reasons cohort studies have assessed shift work rather crudel...
Source: Am J Epidemiol - November 27, 2023 Category: Epidemiology Authors: Kyriaki Papantoniou Johnni Hansen Source Type: research
Correcting for Antibody Waning in Cumulative Incidence Estimation from Sequential Serosurveys
We present an empirically-supported approach for sero-reversion correction in cumulative incidence estimation when sequential serosurveys are conducted in the context of a newly emerging infectious disease. The correction is based on the observed dynamics of antibody titers in sero-positive cases and validated using several in silico test scenarios. Furthermore, through this approach we revise a previous cumulative incidence estimate, which relies on the assumption of an exponentially-declining probability of sero-reversion over time, of SARS-CoV-2 of 76% in Manaus, Brazil, by October 2020 to 47.6% (43.5% - 53.5%). This es...
Source: Am J Epidemiol - November 27, 2023 Category: Epidemiology Authors: Sarah Kadelka Judith A Bouman Peter Ashcroft Roland R Regoes Source Type: research
Longitudinal transitions between combustible, non-combustible, and poly-cannabis product use from adolescence to young adulthood and intersections with nicotine use
This study examined transitions across combustible and non-combustible form of cannabis use and poly-use from adolescence to young adulthood and the role of nicotine use in transitions. In a longitudinal cohort from Southern California (n=3,298; baseline mean[SD] age=16.1[0.4] years) with nine semi-annual survey waves (2015-2021), Markov multistate transition modeling estimated short (two-wave) and long-term (nine-wave) transition probabilities across five cannabis states: never use of any product, prior use with no past 6-month (P6M) use of any product, and P6M exclusive non-combustible, P6M exclusive combustible, and P6M...
Source: Am J Epidemiol - November 20, 2023 Category: Epidemiology Authors: Dae-Hee Han Junhan Cho Erin A Vogel Alyssa F Harlow Alayna P Tackett Sandrah P Eckel Rob McConnell Jessica L Barrington-Trimis Adam M Leventhal Source Type: research
Evaluating a Targeted Minimum Loss-based Estimator for Capture-Recapture Analysis: An Application to HIV Surveillance in San Francisco, CA
Am J Epidemiol. 2023 Nov 17:kwad231. doi: 10.1093/aje/kwad231. Online ahead of print.ABSTRACTCapture-recapture is a common tool in epidemiology to estimate the size of "hidden" populations and correct the under-ascertainment of cases, based on incomplete and overlapping lists of the target population. Log-linear models are often used to estimate the population size yet may produce implausible and unreliable estimates due to model misspecification and small cell sizes. A novel Targeted Minimum Loss-based Estimation (TMLE) model developed for capture-recapture makes several notable improvements to conventional modeling: "tar...
Source: Am J Epidemiol - November 20, 2023 Category: Epidemiology Authors: Paul Wesson Manjari Das Mia Chen Ling Hsu Willi McFarland Edward Kennedy Nicholas P Jewell Source Type: research
Post-acute symptoms 4 months after SARS-CoV-2 infection during the Omicron period: a nationwide Danish questionnaire study
Am J Epidemiol. 2023 Nov 17:kwad225. doi: 10.1093/aje/kwad225. Online ahead of print.ABSTRACTPost-acute symptoms are not uncommon after SARS-CoV-2 infection with pre-Omicron variants. How Omicron and COVID-19 booster vaccination influence the risk of post-acute symptoms is less clear. We analyzed data from the nationwide Danish questionnaire study EFTER-COVID comprising 44,553 individuals ≥15 years old, tested between July 2021 and January 2022, in order to evaluate the association of the Omicron variant and COVID-19 booster vaccination with post-acute symptoms and new-onset general health problems, four months after inf...
Source: Am J Epidemiol - November 20, 2023 Category: Epidemiology Authors: Lampros Spiliopoulos Anna Irene Vedel S ørensen Peter Bager Nete Munk Nielsen J ørgen Vinsløv Hansen Anders Koch Inger Kristine Meder Poul Videbech Steen Ethelberg Anders Hviid Source Type: research
Anti-COVID-19 measures and lifestyle changes during theCOVID-19 pandemic and sleep patterns in the Netherlands: a longitudinal study
Am J Epidemiol. 2023 Nov 17:kwad228. doi: 10.1093/aje/kwad228. Online ahead of print.ABSTRACTAlthough there is scientific evidence for an increased prevalence of sleep disorders during the COVID-19 pandemic, there is still limited information on how lifestyle factors might have affected sleep patterns. Therefore, we followed a large cohort of participants in the Netherlands (n=5,420) for up to one year (September 2020-2021) via monthly web-based questionnaires to identify lifestyle changes (physical activity, smoking, alcohol consumption, electronic device use, and social media use) driven by anti-COVID-19 measures and the...
Source: Am J Epidemiol - November 20, 2023 Category: Epidemiology Authors: Nekane Sandoval-Diez Lidwien A M Smit Jolanda M A Boer Myrna M T de Rooij Gerard H Koppelman Warner van Kersen Judith M Vonk Roel Vermeulen Ulrike Gehring Anke Huss Source Type: research
Does Tobacco Smoking Increase Social Isolation? A Mendelian Randomization Study
This study aimed to investigate the causal effect of smoking on social isolation among older adults in England. Data from older adults of European ancestry who participated in one or more waves from wave 1 (2002/2003) to 9 (2018/2019) of the English Longitudinal Study of Ageing were analyzed (n = 43,687 observations from 7,008 individuals; mean age 68.50). The effect of current smoking on social isolation (ranges from 0 to 5) was estimated by two-stage least squares estimation using a polygenic score (PGS) for smoking cessation as the instrument. A low PGS for smoking cessation predicted current smoking (coefficient per 1 ...
Source: Am J Epidemiol - November 20, 2023 Category: Epidemiology Authors: Yusuke Matsuyama Takahiro Tabuchi Source Type: research
Integrating Data Across Multiple Sites in the Northeastern United States to Examine Associations Between a Prenatal Metal Mixture and Child Cognition
Am J Epidemiol. 2023 Nov 17:kwad233. doi: 10.1093/aje/kwad233. Online ahead of print.ABSTRACTWe applied a novel Hierarchical Bayesian Weighted Quantile Sum (HBWQS) regression to combine data across three sites to examine associations between prenatal metals exposure and cognitive functioning in childhood. Data from 326 mother-child dyads enrolled in the ongoing PRogramming of Intergenerational Stress Mechanisms (PRISM) cohort, based in New York City (recruited 2013-2020) and Boston (recruited 2011-2013), and the First Thousand Days of Life (FTDL) cohort (recruited 2012-2019), based in Northern Virginia were used. Arsenic, ...
Source: Am J Epidemiol - November 20, 2023 Category: Epidemiology Authors: Maria Jos é Rosa Nicolo Foppa Pedretti Brandon Goldson Nicole Mathews Francheska Merced-Nieves Naim Xhani Michelle Bosquet Enlow Richard Gershon Emily Ho Kathi Huddleston Robert O Wright Rosalind J Wright Elena Colicino Source Type: research
Inconsistency in UK Biobank Event Definitions From Different Data Sources and Its Impact on Bias and Generalizability: A Case Study of Venous Thromboembolism
Am J Epidemiol. 2023 Nov 17:kwad232. doi: 10.1093/aje/kwad232. Online ahead of print.ABSTRACTThe UK Biobank study contains several sources of diagnostic data, including hospital inpatient data and self-reported conditions for ~500,000 participants, and primary care data for ~177,000 participants (35%). Epidemiological investigations require a primary disease definition, but whether to combine sources to maximize power or focus on one to ensure a consistent outcome is not clear. The consistency of definitions was investigated for venous thromboembolism (VTE) by looking at overlap when defining cases from hospital in-patient...
Source: Am J Epidemiol - November 20, 2023 Category: Epidemiology Authors: Emily Bassett James Broadbent Dipender Gill Stephen Burgess Amy M Mason Source Type: research
Longitudinal transitions between combustible, non-combustible, and poly-cannabis product use from adolescence to young adulthood and intersections with nicotine use
This study examined transitions across combustible and non-combustible form of cannabis use and poly-use from adolescence to young adulthood and the role of nicotine use in transitions. In a longitudinal cohort from Southern California (n=3,298; baseline mean[SD] age=16.1[0.4] years) with nine semi-annual survey waves (2015-2021), Markov multistate transition modeling estimated short (two-wave) and long-term (nine-wave) transition probabilities across five cannabis states: never use of any product, prior use with no past 6-month (P6M) use of any product, and P6M exclusive non-combustible, P6M exclusive combustible, and P6M...
Source: Am J Epidemiol - November 20, 2023 Category: Epidemiology Authors: Dae-Hee Han Junhan Cho Erin A Vogel Alyssa F Harlow Alayna P Tackett Sandrah P Eckel Rob McConnell Jessica L Barrington-Trimis Adam M Leventhal Source Type: research
Evaluating a Targeted Minimum Loss-based Estimator for Capture-Recapture Analysis: An Application to HIV Surveillance in San Francisco, CA
Am J Epidemiol. 2023 Nov 17:kwad231. doi: 10.1093/aje/kwad231. Online ahead of print.ABSTRACTCapture-recapture is a common tool in epidemiology to estimate the size of "hidden" populations and correct the under-ascertainment of cases, based on incomplete and overlapping lists of the target population. Log-linear models are often used to estimate the population size yet may produce implausible and unreliable estimates due to model misspecification and small cell sizes. A novel Targeted Minimum Loss-based Estimation (TMLE) model developed for capture-recapture makes several notable improvements to conventional modeling: "tar...
Source: Am J Epidemiol - November 20, 2023 Category: Epidemiology Authors: Paul Wesson Manjari Das Mia Chen Ling Hsu Willi McFarland Edward Kennedy Nicholas P Jewell Source Type: research
Post-acute symptoms 4 months after SARS-CoV-2 infection during the Omicron period: a nationwide Danish questionnaire study
Am J Epidemiol. 2023 Nov 17:kwad225. doi: 10.1093/aje/kwad225. Online ahead of print.ABSTRACTPost-acute symptoms are not uncommon after SARS-CoV-2 infection with pre-Omicron variants. How Omicron and COVID-19 booster vaccination influence the risk of post-acute symptoms is less clear. We analyzed data from the nationwide Danish questionnaire study EFTER-COVID comprising 44,553 individuals ≥15 years old, tested between July 2021 and January 2022, in order to evaluate the association of the Omicron variant and COVID-19 booster vaccination with post-acute symptoms and new-onset general health problems, four months after inf...
Source: Am J Epidemiol - November 20, 2023 Category: Epidemiology Authors: Lampros Spiliopoulos Anna Irene Vedel S ørensen Peter Bager Nete Munk Nielsen J ørgen Vinsløv Hansen Anders Koch Inger Kristine Meder Poul Videbech Steen Ethelberg Anders Hviid Source Type: research
