A5015192061- Advanced Causal Inference Techniques
- Statistical Methods and Inference
- Mental Health Research Topics
- Statistical Methods and Bayesian Inference
- Health disparities and outcomes
- Complex Network Analysis Techniques
- Health Systems, Economic Evaluations, Quality of Life
- Bayesian Modeling and Causal Inference
- Statistical Methods in Clinical Trials
- Spatial and Panel Data Analysis
- HIV, Drug Use, Sexual Risk
- HIV/AIDS Research and Interventions
- COVID-19 epidemiological studies
- Substance Abuse Treatment and Outcomes
- Atmospheric and Environmental Gas Dynamics
- Opinion Dynamics and Social Influence
- Air Quality and Health Impacts
- Obesity, Physical Activity, Diet
- Climate Change and Health Impacts
- Data-Driven Disease Surveillance
- COVID-19 Clinical Research Studies
- Forensic and Genetic Research
- Pregnancy and Medication Impact
- Economic and Environmental Valuation
- Genetic Associations and Epidemiology
Johns Hopkins University
2015-2024
Bloomberg (United States)
2015
Brown University
2015
Harvard University
2012-2014
Cancer Research And Biostatistics
2012
Harvard University Press
2012
Columbia University
2007-2008
New York State Psychiatric Institute
2007-2008
National Institute on Alcohol Abuse and Alcoholism
2007
National Institutes of Health
2007
Epidemiologic information is important to inform etiological research and service delivery planning. However, current on the epidemiology of alcohol use disorders in United States lacking.To present nationally representative findings prevalence, correlates, psychiatric comorbidity, treatment DSM-IV abuse dependence.Face-to-face interviews with a US adult sample (N = 43 093).Lifetime 12-month dependence.Prevalence lifetime was 17.8% 4.7%; prevalence dependence 12.5% 3.8%. Alcohol...
Prior research has reported disparities in environmental exposures the United States, but, to our knowledge, no nationwide studies have assessed inequality noise pollution.We aimed a) assess racial/ethnic and socioeconomic inequalities pollution contiguous States; b) consider modifying role of metropolitan level racial residential segregation.We used a geospatial sound model estimate census block group–level median (L50) nighttime daytime exposure 90th percentile (L10) exposure. Block group...
Unconventional natural gas development has expanded rapidly. In Pennsylvania, the number of producing wells increased from 0 in 2005 to 3,689 2013. Few publications have focused on unconventional and birth outcomes. We performed a retrospective cohort study using electronic health record data 9,384 mothers linked 10,946 neonates Geisinger Health System January 2009 estimated cumulative exposure activity with an inverse-distance squared model that incorporated distance mother's home; dates...
Marital discord is costly to children, families, and communities. The advent of the Internet, social networking, on-line dating has affected how people meet future spouses, but little known about prevalence or outcomes these marriages demographics those involved. We addressed questions in a nationally representative sample 19,131 respondents who married between 2005 2012. Results indicate that more than one-third America now begin on-line. In addition, began on-line, when compared with...
We describe semiparametric estimation and inference for causal effects using observational data from a single social network. Our asymptotic results are the first to allow dependence of each observation on growing number other units as sample size increases. In addition, while previous methods have implicitly permitted only one two possible sources among network observations, we both due transmission information across ties latent similarities nodes sharing ties. propose new that...
<h3>Importance</h3> Asthma is common and can be exacerbated by air pollution stress. Unconventional natural gas development (UNGD) has community environmental impacts. In Pennsylvania, UNGD began in 2005, 2012, 6253 wells had been drilled. There are no prior studies of objective respiratory outcomes. <h3>Objective</h3> To evaluate associations between asthma exacerbations. <h3>Design</h3> A nested case-control study comparing patients with without exacerbations from 2005 through 2012 treated...
Mediation analysis is an important tool in the behavioral sciences for investigating role of intermediate variables that lie path between a treatment and outcome variable. The influence variable on often explored using linear structural equation model (LSEM), with coefficients interpreted as possible effects. While there has been significant research topic, little work done when (mediator) high-dimensional vector. In this work, we introduce novel method identifying potential mediators...
We consider estimation of the causal effect a binary treatment on an outcome, conditionally covariates, from observational studies or natural experiments in which there is instrument for treatment. describe doubly robust, locally efficient estimator parameters indexing model local average covariates V when randomization only true high dimensional vector X, possibly bigger than V. discuss surprising result that inference identical to additive treated assumes no treatment-instrument...
Coal and oil power plant retirements reduce air pollution nearby, but few studies have leveraged these natural experiments for public health research. We used California Department of Public Health birth records US Energy Information Administration data from 2001–2011 to evaluate the relationship between 8 coal plants nearby preterm (gestational age <37 weeks) birth. conducted a difference-in-differences analysis using adjusted linear mixed models that included 57,005 births—6.3% which were...
The term "interference" has been used to describe any setting in which one subject's exposure may affect another outcome. We use causal diagrams distinguish among three mechanisms that give rise interference. first mechanism by interference can operate is a direct effect of individual's treatment on outcome; we call this Interference contagion present when outcome the outcomes other individuals with whom he comes into contact. Then giving individual could have an indirect others through...
To characterize prevalence, incidence, and associated correlates of HIV infection among MSM in 12 cities across India.Cross-sectional sample using respondent-driven sampling from September 2012 to June 2013.A total 12022 (~1000/city) were recruited. Participants had be at least 18 years, self-identify as male, report oral/anal intercourse with a man the prior year. was diagnosed three rapid tests. Cross-sectional incidence estimated multiassay algorithm. All estimates incorporate sampling-II...
Abstract “Covariate adjustment” in the randomized trial context refers to an estimator of average treatment effect that adjusts for chance imbalances between study arms baseline variables (called “covariates”). The could include, example, age, sex, disease severity, and biomarkers. According two surveys clinical reports, there is confusion about statistical properties covariate adjustment. We focus on analysis covariance (ANCOVA) estimator, which involves fitting a linear model outcome given...
Since the National Academy of Sciences released their report outlining paths for improving reliability, standards, and policies in forensic sciences (NAS, 2009), there has been heightened interest evaluating scientific validity science disciplines.Guyll et al. (2023) seek to evaluate cartridge-case comparisons.They conducted an experiment test accuracy firearms examiners.They then describe how triers fact such as a judge or jury criminal case, who are initially unbiased have not yet seen any...
Article AbstractObjective: Although emerging data indicate that sample composition may influence the effectiveness of mental health interventions, extent to which subjects in clinical trials represent affected community samples remains unknown. The goal this study was assess proportion community-dwelling adults with major depressive episode (MDE) who would meet eligibility criteria for a traditional efficacy trial patients MDE. Method: We applied standard set exclusion used MDE 2001-2002...
Injecting drug use has historically been the principal driver of HIV epidemic in northeast states India. However, recent data indicate growing numbers people who inject drugs (PWIDs) north and central Indian cities.We conducted face-to-face surveys among PWIDs seven eight north/central cities using respondent-driven sampling. We used a rapid HIV-testing protocol to identify seropositive individuals multiassay algorithm those with infection. multilevel regression models that incorporated...
Radon is the second-leading cause of lung cancer worldwide. Most indoor exposure occurs by diffusion soil gas. also found in well water, natural gas, and ambient air. Pennsylvania has high radon concentrations; buildings are often tested during real estate transactions, with results reported to Department Environmental Protection (PADEP).We evaluated predictors concentrations.Using first-floor basement PADEP between 1987 2013, we associations concentrations (natural log transformed) geology,...
Demographic and Health Surveys (DHS) conducted throughout sub-Saharan Africa indicate there is widespread acceptance of intimate partner violence, contributing to an adverse health risk environment for women. While qualitative studies suggest important limitations in the accuracy DHS methods used elicit attitudes toward date has been little experimental evidence from that can be brought bear on this issue.We embedded a randomized survey experiment population-based 1,334 adult men women...
Consider the causal effect that one individual’s treatment may have on another outcome when is contagious, with specific application to of vaccination an infectious disease outcome. The another’s can be decomposed into two different effects, called “infectiousness” and “contagion” effects. We present identifying assumptions estimation or testing procedures for infectiousness contagion effects in settings: (1) using data sampled from independent groups observations, (2) collected a single...
Consider a study with binary exposure, outcome, and confounder, where the confounder is nondifferentially misclassified. Epidemiologists have long accepted unproven but oft-cited result that, if binary, then odds ratios, risk differences that control for mismeasured will lie between crude true measures. In this paper, we provide an analytic proof of in absence qualitative interaction treatment demonstrate via counterexample need not hold when there such interaction. We also present effect...
Traditionally, statistical inference and causal on human subjects rely the assumption that individuals are independently affected by treatments or exposures. However, recently there has been increasing interest in settings, such as social networks, where may interact with one another spill over from treated individual to their contacts outcomes be contagious. Existing models proposed for using observational data networks of interacting have two major shortcomings. First, they often require a...