Medicine and Health Sciences Commons^™

A Hybrid Model For Reducing Ecological Bias, Ruth Salway, Jon Wakefield

UW Biostatistics Working Paper Series

A major drawback of epidemiological ecological studies, in which the association between area-level summaries of risk and exposure are used to make inference about individual risk, is the difficulty in characterising within-area variability in exposure and confounder variables. To avoid ecological bias, samples of individual exposure/confounder data within each area are required. Unfortunately these may be difficult or expensive to obtain, particularly if large samples are required. In this paper we propose a new approach suitable for use with small samples. We combine a Bayesian non-parametric Dirichlet process prior with an estimating functions approach, and show that this model gives …

Health-Exposure Modelling And The Ecological Fallacy, Jon Wakefield, Gavin Shaddick

UW Biostatistics Working Paper Series

Recently there has been increased interest in modelling the association between aggregate disease counts and environmental exposures measured, for example via air pollution monitors, at point locations. This paper has two aims: first we develop a model for such data in order to avoid ecological bias; second we illustrate that modelling the exposure surface and estimating exposures may lead to bias in estimation of health effects. Design issues are also briefly considered, in particular the loss of information in moving from individual to ecological data, and the at-risk populations to consider in relation to the pollution monitor locations. The approach …

Ua12/2/1 College Heights Herald, Vol. 81, No. 23 [25], Wku Student Affairs

WKU Archives Records

WKU campus newspaper reporting campus, athletic and Bowling Green, Kentucky news. Articles in this issue:

• Leslie, Joey. More Students Tested During AIDS Day
• Hupman, Samantha. J-term More Popular than Anticipated
• Fontana, Alex. Student Government Association Proposes New Bicycles for Police
• Bosken, Nina. Students Dodge, Duck, Dive for Charity and Prizes – Special Olympics
• Richardson, Kelly. Kentucky Community Technical College System Requests Funding – KCTCS
• Taking the Next Step – Cultural Diversity
• Eoff, Allison. Pass on Adderall
• Gabler, R. XXX Ads Disappointing
• Williams, Suzanne. A Woman’s Heart
• Hupman, Samantha. Two Fights Reported on Hill
• Paul, Corey. Kwanzaa to Be Celebrated Today …

History-Adjusted Marginal Structural Models To Estimate Time-Varying Effect Modification , Maya L. Petersen, Steven G. Deeks, Jeffrey N. Martin, Mark J. Van Der Laan

U.C. Berkeley Division of Biostatistics Working Paper Series

Much of epidemiology and clinical medicine is focused on the estimation of treatments or interventions administered over time. In such settings of longitudinal treatment, time-dependent confounding is often an important source of bias. Marginal structural models are a powerful tool for estimating the causal effect of a treatment using observational data, particularly when time-dependent confounding is present. Recent statistical work presented a generalization of marginal structural models, called history-adjusted marginal structural models. Unlike standard marginal structural models, history-adjusted marginal structural models can be used to estimate modification of treatment effects by time-varying covariates. Estimation of time-dependent causal effect modification is …

Genotype-By-Sex Interaction In The Regulation Of High-Density Lipoprotein: Theframingham Heart Study, M.J. Mosher, L. J. Martin, L. A. Cupples, Q. Yang, T. D. Dyer, J. T. Williams, K. E. North

Anthropology Faculty and Staff Publications

Low levels of high-density lipoprotein (HDL) are widely documented as a risk factor for cardiovascular disease (CVD). Furthermore, there is marked sexual dimorphism in both HDL levels and the prevalence of CVD. However, the extent to which genetic factors contribute to such dimorphism has been largely unexplored. We examined the evidence for genotypeby- sex effects on HDL in a longitudinal sample of 1,562 participants from 330 families in the Framingham Heart Study at three times points corresponding approximately to 1971-1974, 1980-1983, and 1988-1991. Using a variance component method, we conducted a genome scan of HDL at each time point in …

What Is Comprehensive Sexuality Education Really All About? Perceptions Of Students Enrolled In An Undergraduate Human Sexuality Course, Eva Goldfarb

Department of Public Health Scholarship and Creative Works

The purpose of this study was to use qualitative evaluation techniques to explore the perceptions of students enrolled in undergraduate human sexuality classes regarding their expectations for the course as well as outcomes. One hundred forty-eight students were surveyed at the beginning and again at the end of the semester-long course. While pregnancy and STI prevention were considered important components of their courses, other outcomes associated with positive, healthy sexuality were given greater emphasis. Results suggest that while primary and secondary level sexuality education have been increasingly focused on abstinence-only education with a focus on pregnancy and STI reduction, this …

Oral Contraceptive Use And Risk Of Breast Cancer Among Women With A Family History Of Breast Cancer: A Prospective Cohort Study, Stephanie A. Navarro Silvera, Anthony B. Miller, Thomas E. Rohan

Department of Public Health Scholarship and Creative Works

Family history of breast cancer is an established risk factor for breast cancer. In addition, there is evidence that oral contraceptive use may be associated with a moderate increase in breast cancer risk. The three cohort studies that have investigated the relationship between oral contraceptive use and breast cancer risk among women with a family history of breast cancer have yielded mixed results, possibly due to the relatively small sample sizes employed and/or differences in the selection of covariates for inclusion in multivariate models. Therefore, we examined the association between oral contraceptive use and breast cancer risk in a large …

Population Intervention Models In Causal Inference, Alan E. Hubbard, Mark J. Van Der Laan

U.C. Berkeley Division of Biostatistics Working Paper Series

Marginal structural models (MSM) provide a powerful tool for estimating the causal effect of a] treatment variable or risk variable on the distribution of a disease in a population. These models, as originally introduced by Robins (e.g., Robins (2000a), Robins (2000b), van der Laan and Robins (2002)), model the marginal distributions of treatment-specific counterfactual outcomes, possibly conditional on a subset of the baseline covariates, and its dependence on treatment. Marginal structural models are particularly useful in the context of longitudinal data structures, in which each subject's treatment and covariate history are measured over time, and an outcome is recorded at …

Additive Hazards Models With Latent Treatment Effectiveness Lag Time, Ying Qing Chen, Charles A. Rohde, Mei-Cheng Wang

Johns Hopkins University, Dept. of Biostatistics Working Papers

In many clinical trials to evaluate treatment efficacy, it is believed that there may exist latent treatment effectiveness lag times after which medical procedure or chemical compound would be in full effect. In this article, semiparametric regression models are proposed and studied to estimate the treatment effect accounting for such latent lag times. The new models take advantage of the invariance property of the additive hazards model in marginalizing over random effects, so parameters in the models are easy to be estimated and interpreted, while the flexibility without specifying baseline hazard function is kept. Monte Carlo simulation studies demonstrate the …

Gauss-Seidel Estimation Of Generalized Linear Mixed Models With Application To Poisson Modeling Of Spatially Varying Disease Rates, Subharup Guha, Louise Ryan

Harvard University Biostatistics Working Paper Series

Generalized linear mixed models (GLMMs) provide an elegant framework for the analysis of correlated data. Due to the non-closed form of the likelihood, GLMMs are often fit by computational procedures like penalized quasi-likelihood (PQL). Special cases of these models are generalized linear models (GLMs), which are often fit using algorithms like iterative weighted least squares (IWLS). High computational costs and memory space constraints often make it difficult to apply these iterative procedures to data sets with very large number of cases.

This paper proposes a computationally efficient strategy based on the Gauss-Seidel algorithm that iteratively fits sub-models of the GLMM …

Cigarette Smoking And Risk Of Glioma: A Prospective Cohort Study, Stephanie A. Navarro Silvera, Anthony B. Miller, Thomas E. Rohan

Department of Public Health Scholarship and Creative Works

The etiology of glioma, the most commonly diagnosed malignant brain tumor among adults in the United States, is poorly understood. N‐nitroso compounds are known carcinogens, which are found in cigarette smoke and can induce gliomas in rats. On this basis, it has been hypothesized that cigarette smoking may be associated with an increased risk of glioma. We investigated the association between cigarette smoking and glioma risk in the National Breast Screening Study, which included 89,835 Canadian women aged 40–59 years at recruitment between 1980 and 1985. Linkages to national cancer and mortality databases yielded data on cancer incidence and deaths …

Cigarette Smoking And Risk Of Glioma: A Prospective Cohort Study, Stephanie A. Navarro Silvera, Anthony B. Miller, Thomas E. Rohan

Department of Public Health Scholarship and Creative Works

The etiology of glioma, the most commonly diagnosed malignant brain tumor among adults in the United States, is poorly understood. N‐nitroso compounds are known carcinogens, which are found in cigarette smoke and can induce gliomas in rats. On this basis, it has been hypothesized that cigarette smoking may be associated with an increased risk of glioma. We investigated the association between cigarette smoking and glioma risk in the National Breast Screening Study, which included 89,835 Canadian women aged 40–59 years at recruitment between 1980 and 1985. Linkages to national cancer and mortality databases yielded data on cancer incidence and deaths …

Computational Techniques For Spatial Logistic Regression With Large Datasets, Christopher J. Paciorek, Louise Ryan

Harvard University Biostatistics Working Paper Series

In epidemiological work, outcomes are frequently non-normal, sample sizes may be large, and effects are often small. To relate health outcomes to geographic risk factors, fast and powerful methods for fitting spatial models, particularly for non-normal data, are required. We focus on binary outcomes, with the risk surface a smooth function of space. We compare penalized likelihood models, including the penalized quasi-likelihood (PQL) approach, and Bayesian models based on fit, speed, and ease of implementation.

A Bayesian model using a spectral basis representation of the spatial surface provides the best tradeoff of sensitivity and specificity in simulations, detecting real spatial …

Estimation And Projection Of Indicence And Prevalence Based On Doubly Truncated Data With Application To Pharmacoepidemiological Databases, Henrik Stovring, Mei-Cheng Wang

Johns Hopkins University, Dept. of Biostatistics Working Papers

Incidences of disease are of primary interest in any epidemiological analysis of disease spread in general populations. Ordinary estimates obtained from follow-up of an initially non-diseased cohort are costly, and so such estimates are not routinely available. In contrast, routine registers exist for many diseases with data on all detected cases within a given calendar time period, but lacking information on non-diseased. In the present work we show how this type of data supplemented with data on the past birth process can be analyzed to yield age specific incidence estimates as well as lifetime prevalence. A non-parametric model is studied …

Estimation Of Direct Causal Effects, Maya L. Petersen, Mark J. Van Der Laan

U.C. Berkeley Division of Biostatistics Working Paper Series

Many common problems in epidemiologic and clinical research involve estimating the effect of an exposure on an outcome while blocking the exposure's effect on an intermediate variable. Effects of this kind are termed direct effects. Estimation of direct effects arises frequently in research aimed at understanding mechanistic pathways by which an exposure acts to cause or prevent disease, as well as in many other settings. Although multivariable regression is commonly used to estimate direct effects, this approach requires assumptions beyond those required for the estimation of total causal effects. In addition, multivariable regression estimates a particular type of direct effect, …

A Nonstationary Negative Binomial Time Series With Time-Dependent Covariates: Enterococcus Counts In Boston Harbor, E. Andres Houseman, Brent Coull, James P. Shine

Harvard University Biostatistics Working Paper Series

Boston Harbor has had a history of poor water quality, including contamination by enteric pathogens. We conduct a statistical analysis of data collected by the Massachusetts Water Resources Authority (MWRA) between 1996 and 2002 to evaluate the effects of court-mandated improvements in sewage treatment. Motivated by the ineffectiveness of standard Poisson mixture models and their zero-inflated counterparts, we propose a new negative binomial model for time series of Enterococcus counts in Boston Harbor, where nonstationarity and autocorrelation are modeled using a nonparametric smooth function of time in the predictor. Without further restrictions, this function is not identifiable in the presence …

Direct Effect Models, Mark J. Van Der Laan, Maya L. Petersen

U.C. Berkeley Division of Biostatistics Working Paper Series

The causal effect of a treatment on an outcome is generally mediated by several intermediate variables. Estimation of the component of the causal effect of a treatment that is mediated by a given intermediate variable (the indirect effect of the treatment), and the component that is not mediated by that intermediate variable (the direct effect of the treatment) is often relevant to mechanistic understanding and to the design of clinical and public health interventions. Under the assumption of no-unmeasured confounders for treatment and the intermediate variable, Robins & Greenland (1992) define an individual direct effect as the counterfactual effect of …

Inequalities In Neighbourhood Socioeconomic Characteristics: Potential Evidence-Base For Neighbourhood Health Planning., Agricola Odoi, R Wray, M Emo, S Birch, B Hutchison, J Eyles, T Abernathy

Faculty Publications and Other Works -- Biomedical and Diagnostic Sciences

BACKGROUND: Population health planning aims to improve the health of the entire population and to reduce health inequities among population groups. Socioeconomic factors are increasingly being recognized as major determinants of many aspects of health and causes of health inequities. Knowledge of socioeconomic characteristics of neighbourhoods is necessary to identify their unique health needs and enhance identification of socioeconomically disadvantaged populations. Careful integration of this knowledge into health planning activities is necessary to ensure that health planning and service provision are tailored to unique neighbourhood population health needs. In this study, we identify unique neighbourhood socioeconomic characteristics and classify the …

Dietary Folate, Alcohol Consumption, And Risk Of Ovarian Cancer In An Italian Case-Control Study, Claudio Pelucchi, Monia Mereghetti, Renato Talamini, Eva Negri, Maurizio Montella, Valerio Ramazzotti, Silvia Franceschi, Carlo La Vecchia

Department of Public Health Scholarship and Creative Works

An increasing number of studies are focusing on the potential association between dietary folate intake and risk of various cancers (1), particularly of the colorectum and breast (2, 3). A low folate status can induce misincorporation of uracil into DNA, leading to chromosome breaks in humans and hence increasing cancer risk (4). Alcohol may increase folate requirements in the body and cause relative folate deficiencies (2). Although several findings on the relation between folate intake and ovarian cancer risk are inconsistent (5-9), recent results from two prospective …

Self-Management Strategies Mediate Self-Efficacy And Physical Activity, Rod K. Dishman, Robert W. Motl, James F. Sallis, Andrea L. Dunn, Amanda Birnbaum, Greg J. Welk, Ariane L. Bedimo-Rung, Carolyn C. Voorhees, Jared B. Jobe

Department of Public Health Scholarship and Creative Works

Background

Self-efficacy theory proposes that girls who have confidence in their capability to be physically active will perceive fewer barriers to physical activity or be less influenced by them, be more likely to pursue perceived benefits of being physically active, and be more likely to enjoy physical activity. Self-efficacy is theorized also to influence physical activity through self-management strategies (e.g., thoughts, goals, plans, and acts) that support physical activity, but this idea has not been empirically tested.

Methods

Confirmatory factor analysis was used to test the factorial validity of a measure of self-management strategies for physical activity. Next, the construct …

Risk Factors For Thyroid Cancer: A Prospective Cohort Study, Stephanie A. Navarro Silvera, Anthony B. Miller, Thomas E. Rohan

Department of Public Health Scholarship and Creative Works

Given the higher incidence rate of thyroid cancer among women compared to men and evidence that smoking and alcohol consumption may be inversely related to thyroid cancer risk, we examined thyroid cancer risk in association with menstrual, reproductive, and hormonal factors, and cigarette and alcohol consumption, in a prospective cohort study of 89,835 Canadian women aged 40–59 at recruitment who were enrolled in the National Breast Screening Study (NBSS). Linkages to national cancer and mortality databases yielded data on cancer incidence and deaths from all causes, respectively, with follow-up ending between 1998 and 2000. Cox proportional hazards models (using age …

Attributable Risk Function In The Proportional Hazards Model, Ying Qing Chen, Chengcheng Hu, Yan Wang

UW Biostatistics Working Paper Series

As an epidemiological parameter, the population attributable fraction is an important measure to quantify the public health attributable risk of an exposure to morbidity and mortality. In this article, we extend this parameter to the attributable fraction function in survival analysis of time-to-event outcomes, and further establish its estimation and inference procedures based on the widely used proportional hazards models. Numerical examples and simulations studies are presented to validate and demonstrate the proposed methods.

Glycemic Index, Glycemic Load, And Pancreatic Cancer Risk (Canada), Stephanie A. Navarro Silvera, Thomas E. Rohan, Meera Jain, Paul D. Terry, Geoffrey R. Howe, Anthony B. Miller

Department of Public Health Scholarship and Creative Works

There is some evidence that plasma insulin and post-load plasma glucose may be associated with the risk of pancreatic cancer. Glycemic index and glycemic load are measures, which allow the carbohydrate content of individual foods to be classified according to their postprandial glycemic effects and hence their effects on circulating insulin levels. Therefore, we examined pancreatic cancer risk in association with a glycemic index (GI), glycemic load (GL), and intake of dietary carbohydrate and sugar in a prospective cohort of 49,613 Canadian women enrolled in the National Breast Screening Study (NBSS) who completed a self-administered food frequency questionnaire between 1980 …

Scale Development For Perceived School Climate For Girls’ Physical Activity, Amanda Birnbaum, Kelly R. Evenson, Robert W. Motl, Rod K. Dishman, Carolyn C. Voorhees, James F. Sallis, John P. Elder, Marsha Dowda

Department of Public Health Scholarship and Creative Works

Objectives: To test an original scale assessing perceived school climate for girls' physical activity in middle school girls. Methods: Confirmatory factor analysis (CFA) and structural equation modeling (SEM). Results: CFA retained 5 of 14 original items. A model with 2 correlated factors, perceptions about teachers' and boys' behaviors, respectively, fit the data well in both sixth and eighth-graders. SEM detected a positive, significant direct association of the teacher factor, but not the boy factor, with girls' self-reported physical activity. Conclusions: School climate for girls' physical activity is a measurable construct, and preliminary evidence suggests a relationship with physical activity.

Glycemic Index, Glycemic Load, And Pancreatic Cancer Risk (Canada), Stephanie A. Navarro Silvera, Thomas E. Rohan, Meera Jain, Paul D. Terry, Geoffrey R. Howe, Anthony B. Miller

Department of Public Health Scholarship and Creative Works

There is some evidence that plasma insulin and post-load plasma glucose may be associated with the risk of pancreatic cancer. Glycemic index and glycemic load are measures, which allow the carbohydrate content of individual foods to be classified according to their postprandial glycemic effects and hence their effects on circulating insulin levels. Therefore, we examined pancreatic cancer risk in association with a glycemic index (GI), glycemic load (GL), and intake of dietary carbohydrate and sugar in a prospective cohort of 49,613 Canadian women enrolled in the National Breast Screening Study (NBSS) who completed a self-administered food frequency questionnaire between 1980 …

Glycemic Index, Glycemic Load, And Pancreatic Cancer Risk (Canada), Stephanie A. Navarro Silvera, Thomas E. Rohan, Meera Jain, Paul D. Terry, Geoffrey R. Howe, Anthony B. Miller

Department of Public Health Scholarship and Creative Works

There is some evidence that plasma insulin and post-load plasma glucose may be associated with the risk of pancreatic cancer. Glycemic index and glycemic load are measures, which allow the carbohydrate content of individual foods to be classified according to their postprandial glycemic effects and hence their effects on circulating insulin levels. Therefore, we examined pancreatic cancer risk in association with a glycemic index (GI), glycemic load (GL), and intake of dietary carbohydrate and sugar in a prospective cohort of 49,613 Canadian women enrolled in the National Breast Screening Study (NBSS) who completed a self-administered food frequency questionnaire between 1980 …

Scale Development For Perceived School Climate For Girls’ Physical Activity, Amanda Birnbaum, Kelly R. Evenson, Robert W. Motl, Rod K. Dishman, Carolyn C. Voorhees, James F. Sallis, John P. Elder, Marsha Dowda

Department of Public Health Scholarship and Creative Works

Objectives: To test an original scale assessing perceived school climate for girls' physical activity in middle school girls. Methods: Confirmatory factor analysis (CFA) and structural equation modeling (SEM). Results: CFA retained 5 of 14 original items. A model with 2 correlated factors, perceptions about teachers' and boys' behaviors, respectively, fit the data well in both sixth and eighth-graders. SEM detected a positive, significant direct association of the teacher factor, but not the boy factor, with girls' self-reported physical activity. Conclusions:School climate for girls' physical activity is a measurable construct, and preliminary evidence suggests a relationship with physical activity.

Causal Inference In Longitudinal Studies With History-Restricted Marginal Structural Models, Romain Neugebauer, Mark J. Van Der Laan, Ira B. Tager

U.C. Berkeley Division of Biostatistics Working Paper Series

Causal Inference based on Marginal Structural Models (MSMs) is particularly attractive to subject-matter investigators because MSM parameters provide explicit representations of causal effects. We introduce History-Restricted Marginal Structural Models (HRMSMs) for longitudinal data for the purpose of defining causal parameters which may often be better suited for Public Health research. This new class of MSMs allows investigators to analyze the causal effect of a treatment on an outcome based on a fixed, shorter and user-specified history of exposure compared to MSMs. By default, the latter represents the treatment causal effect of interest based on a treatment history defined by the …

History-Adjusted Marginal Structural Models: Time-Varying Effect Modification, Maya L. Petersen, Mark J. Van Der Laan

U.C. Berkeley Division of Biostatistics Working Paper Series

Marginal structural models (MSM) provide a powerful tool for estimating the causal effect of a treatment, particularly in the context of longitudinal data structures. These models, introduced by Robins, model the marginal distributions of treatment-specific counterfactual outcomes, possibly conditional on a subset of the baseline covariates. However, standard MSM cannot incorporate modification of treatment effects by time-varying covariates. In the context of clinical decision- making such time-varying effect modifiers are often of considerable interest, as they are used in practice to guide treatment decisions for an individual. In this article we introduce a generalization of marginal structural models, which we …

History-Adjusted Marginal Structural Models: Optimal Treatment Strategies, Maya L. Petersen, Mark J. Van Der Laan

U.C. Berkeley Division of Biostatistics Working Paper Series

Much of clinical medicine involves choosing a future treatment plan that is expected to optimize a patient's long-term outcome, and modifying this treatment plan over time in response to changes in patient characteristics. However, dynamic treatment regimens, or decision rules for altering treatment in response to time-varying covariates, are rarely estimated based on observational data. In a companion paper, we introduced a generalization of Marginal Structural Models, named History-Adjusted Marginal Structural Models, that estimate modification of causal effects by time-varying covariates. Here, we illustrate how History-Adjusted Marginal Structural Models can be used to identify a specific type of optimal dynamic …