-
American Journal of Epidemiology Jun 2006Despite the growing popularity of propensity score (PS) methods in epidemiology, relatively little has been written in the epidemiologic literature about the problem of...
Despite the growing popularity of propensity score (PS) methods in epidemiology, relatively little has been written in the epidemiologic literature about the problem of variable selection for PS models. The authors present the results of two simulation studies designed to help epidemiologists gain insight into the variable selection problem in a PS analysis. The simulation studies illustrate how the choice of variables that are included in a PS model can affect the bias, variance, and mean squared error of an estimated exposure effect. The results suggest that variables that are unrelated to the exposure but related to the outcome should always be included in a PS model. The inclusion of these variables will decrease the variance of an estimated exposure effect without increasing bias. In contrast, including variables that are related to the exposure but not to the outcome will increase the variance of the estimated exposure effect without decreasing bias. In very small studies, the inclusion of variables that are strongly related to the exposure but only weakly related to the outcome can be detrimental to an estimate in a mean squared error sense. The addition of these variables removes only a small amount of bias but can increase the variance of the estimated exposure effect. These simulation studies and other analytical results suggest that standard model-building tools designed to create good predictive models of the exposure will not always lead to optimal PS models, particularly in small studies.
Topics: Confounding Factors, Epidemiologic; Effect Modifier, Epidemiologic; Epidemiologic Methods; Humans; Models, Statistical; Monte Carlo Method; Regression Analysis
PubMed: 16624967
DOI: 10.1093/aje/kwj149 -
Revista Espanola de Salud Publica Oct 2017Estimating the prevalence of the so-called "hidden populations" can be challenging, because the identification of its members is difficult due to their socially... (Review)
Review
Estimating the prevalence of the so-called "hidden populations" can be challenging, because the identification of its members is difficult due to their socially sanctionable or illegal behaviors. This article provides a critical review of the most widely used methods for estimating the size of a hard-to-reach population. All are indirect methods, based on incomplete data sources. Depending on the available data, one method can be more appropriate than another. Besides, each method must fulfill a number of requirements, and each one may be subject to specific risk of bias. To choose the most suitable method, an accurate evaluation of the available data is necessary, and. if possible several methods should be used simultaneously to be able to compare the results and to critically evaluate if these results fit with the reality.
Topics: Epidemiologic Methods; Humans; Prevalence; Social Marginalization; Social Stigma; Spain; Undocumented Immigrants; Vulnerable Populations
PubMed: 29066709
DOI: No ID Found -
Epidemiologic Reviews Jan 2022In many perinatal pharmacoepidemiologic studies, exposure to a medication is classified as "ever exposed" versus "never exposed" within each trimester or even over the... (Review)
Review
In many perinatal pharmacoepidemiologic studies, exposure to a medication is classified as "ever exposed" versus "never exposed" within each trimester or even over the entire pregnancy. This approach is often far from real-world exposure patterns, may lead to exposure misclassification, and does not to incorporate important aspects such as dosage, timing of exposure, and treatment duration. Alternative exposure modeling methods can better summarize complex, individual-level medication use trajectories or time-varying exposures from information on medication dosage, gestational timing of use, and frequency of use. We provide an overview of commonly used methods for more refined definitions of real-world exposure to medication use during pregnancy, focusing on the major strengths and limitations of the techniques, including the potential for method-specific biases. Unsupervised clustering methods, including k-means clustering, group-based trajectory models, and hierarchical cluster analysis, are of interest because they enable visual examination of medication use trajectories over time in pregnancy and complex individual-level exposures, as well as providing insight into comedication and drug-switching patterns. Analytical techniques for time-varying exposure methods, such as extended Cox models and Robins' generalized methods, are useful tools when medication exposure is not static during pregnancy. We propose that where appropriate, combining unsupervised clustering techniques with causal modeling approaches may be a powerful approach to understanding medication safety in pregnancy, and this framework can also be applied in other areas of epidemiology.
Topics: Cluster Analysis; Female; Humans; Pharmacoepidemiology; Pregnancy; Pregnancy Trimesters
PubMed: 34100086
DOI: 10.1093/epirev/mxab002 -
Annual Review of Public Health Apr 2012Understanding the impact of place on health is a key element of epidemiologic investigation, and numerous tools are being employed for analysis of spatial health-related... (Review)
Review
Understanding the impact of place on health is a key element of epidemiologic investigation, and numerous tools are being employed for analysis of spatial health-related data. This review documents the huge growth in spatial epidemiology, summarizes the tools that have been employed, and provides in-depth discussion of several methods. Relevant research articles for 2000-2010 from seven epidemiology journals were included if the study utilized a spatial analysis method in primary analysis (n = 207). Results summarized frequency of spatial methods and substantive focus; graphs explored trends over time. The most common spatial methods were distance calculations, spatial aggregation, clustering, spatial smoothing and interpolation, and spatial regression. Proximity measures were predominant and were applied primarily to air quality and climate science and resource access studies. The review concludes by noting emerging areas that are likely to be important to future spatial analysis in public health.
Topics: Demography; Environmental Monitoring; Epidemiologic Methods; Epidemiologic Research Design; Epidemiological Monitoring; Geographic Information Systems; Humans; Regression Analysis; Space-Time Clustering
PubMed: 22429160
DOI: 10.1146/annurev-publhealth-031811-124655 -
American Journal of Public Health Mar 2015We reviewed the use of agent-based modeling (ABM), a systems science method, in understanding noncommunicable diseases (NCDs) and their public health risk factors. We... (Review)
Review
We reviewed the use of agent-based modeling (ABM), a systems science method, in understanding noncommunicable diseases (NCDs) and their public health risk factors. We systematically reviewed studies in PubMed, ScienceDirect, and Web of Sciences published from January 2003 to July 2014. We retrieved 22 relevant articles; each had an observational or interventional design. Physical activity and diet were the most-studied outcomes. Often, single agent types were modeled, and the environment was usually irrelevant to the studied outcome. Predictive validation and sensitivity analyses were most used to validate models. Although increasingly used to study NCDs, ABM remains underutilized and, where used, is suboptimally reported in public health studies. Its use in studying NCDs will benefit from clarified best practices and improved rigor to establish its usefulness and facilitate replication, interpretation, and application.
Topics: Chronic Disease; Databases, Bibliographic; Epidemiologic Methods; Evidence-Based Medicine; Humans; Models, Theoretical; Motor Activity; Risk Factors
PubMed: 25602871
DOI: 10.2105/AJPH.2014.302426 -
Epidemiology (Cambridge, Mass.) Jul 2017Cohort studies can be biased by unmeasured confounding. We propose a hybrid ecologic-epidemiologic design called the trend-in-trend design, which requires a strong time... (Review)
Review
Cohort studies can be biased by unmeasured confounding. We propose a hybrid ecologic-epidemiologic design called the trend-in-trend design, which requires a strong time trend in exposure, but is unbiased unless there are unmeasured factors affecting outcome for which there are time trends in prevalence that are correlated with time trends in exposure across strata with different exposure trends. Thus, the conditions under which the trend-in-trend study is biased are a subset of those under which a cohort study is biased. The trend-in-trend design first divides the study population into strata based on the cumulative probability of exposure given covariates, which effectively stratifies on time trend in exposure, provided there is a trend. Next, a covariates-free maximum likelihood model estimates the odds ratio (OR) using data on exposure prevalence and outcome frequency within cumulative probability of exposure strata, across multiple periods. In simulations, the trend-in-trend design produced ORs with negligible bias in the presence of unmeasured confounding. In empiric applications, trend-in-trend reproduced the known positive association between rofecoxib and myocardial infarction (observed OR: 1.2, 95% confidence interval: 1.1, 1.4), and known null associations between rofecoxib and severe hypoglycemia (OR = 1.1 [0.92, 1.3]) and nonvertebral fracture (OR = 0.84 [0.64, 1.1]). The trend-in-trend method may be useful in settings where there is a strong time trend in exposure, such as a newly approved drug or other medical intervention. See video abstract at, http://links.lww.com/EDE/B178.
Topics: Bias; Cohort Studies; Confounding Factors, Epidemiologic; Epidemiologic Methods; Epidemiologic Research Design; Female; Humans; Likelihood Functions; Male; Odds Ratio
PubMed: 27775954
DOI: 10.1097/EDE.0000000000000579 -
Journal of Nutritional Science 2021Countries are increasingly transitioning from event-based vitamin A supplementation (VAS) distribution to delivery through routine health system contacts, shifting also... (Review)
Review
Countries are increasingly transitioning from event-based vitamin A supplementation (VAS) distribution to delivery through routine health system contacts, shifting also to administrative, electronic-based monitoring tools, a process that brings certain limitations affecting the quality of administrative VAS coverage. At present, there is no standardised methodology for measuring the coverage of VAS delivered through routine health services. To address this gap, we conducted a systematic review of the literature to identify and recommend methods to measure VAS coverage, with the aim of providing guidance to countries on the collection of consistent data for planning, monitoring and evaluating VAS programmes integrated into routine health systems. We searched the PubMed®, Embase®, Scopus, Google Scholar and World Health Organization (WHO) Global Index Medicus databases for studies published from 1 January 2000 to 1 January 2021, reporting original data on VAS coverage and methodologies used for measurement. We screened 2371 original titles and abstracts, assessed twenty-seven full-text articles and ultimately included eighteen studies. All but two studies used a coverage cluster survey (CCS) design to measure VAS coverage, adapting the WHO Vaccination Coverage Cluster Surveys methodology, by modifying sample size and sampling parameters. Annual two-dose VAS coverage was reported from only four studies. Until electronic-based systems to collect and analyse VAS data are equipped to measure routine two-dose VAS coverage using administrative data, CCSs that comply with the 2018 WHO Vaccination Coverage Cluster Surveys Reference Manual represent the gold-standard method for effective VAS programme monitoring.
Topics: Dietary Supplements; Humans; Surveys and Questionnaires; Vitamin A; Vitamin A Deficiency
PubMed: 34527226
DOI: 10.1017/jns.2021.65 -
Survey of Ophthalmology 1986A major limitation in epidemiologic research on the etiology of cataracts is the lack of a standardized method for detecting and grading in vivo cataracts. This article... (Review)
Review
A major limitation in epidemiologic research on the etiology of cataracts is the lack of a standardized method for detecting and grading in vivo cataracts. This article reviews both clinical and photographic methods for determining the presence and severity of cataracts. Clinical methods, involving uniform training of examining ophthalmologists and standard protocols, do not insure reproducibility in detecting or grading cataracts. Photographic methods appear to be more reliable, but more research is needed to develop methods for accurate interpretation.
Topics: Cataract; Epidemiologic Methods; Humans; Photography; Research
PubMed: 3544294
DOI: 10.1016/0039-6257(86)90037-8 -
American Journal of Epidemiology May 2021In aspiring to be discerning epidemiologists, we must learn to think critically about the fundamental concepts in our field and be able to understand and apply many of...
In aspiring to be discerning epidemiologists, we must learn to think critically about the fundamental concepts in our field and be able to understand and apply many of the novel methods being developed today. We must also find effective ways to teach both basic and advanced topics in epidemiology to graduate students, in a manner that goes beyond simple provision of knowledge. Here, we argue that simulation is one critical tool that can be used to help meet these goals, by providing examples of how simulation can be used to address 2 common misconceptions in epidemiology. First, we show how simulation can be used to explore nondifferential exposure misclassification. Second, we show how an instructor could use simulation to provide greater clarity on the correct definition of the P value. Through these 2 examples, we highlight how simulation can be used to both clearly and concretely demonstrate theoretical concepts, as well as to test and experiment with ideas, theories, and methods in a controlled environment. Simulation is therefore useful not only in the classroom but also as a skill for independent self-learning.
Topics: Bias; Confounding Factors, Epidemiologic; Epidemiology; Humans; Monte Carlo Method; Simulation Training
PubMed: 33083814
DOI: 10.1093/aje/kwaa232 -
Annals of Epidemiology Mar 2022A growing area of research in epidemiology is the identification of health-related sibling spillover effects, or the effect of one individual's exposure on their...
PURPOSE
A growing area of research in epidemiology is the identification of health-related sibling spillover effects, or the effect of one individual's exposure on their sibling's outcome. The health within families may be confounded by unobserved factors, rendering identification of sibling spillovers challenging.
METHODS
We demonstrate a gain-score (fixed effects) regression method for identifying exposure-to-outcome spillover effects within sibling pairs in linear models. The method identifies the exposure-to-outcome spillover effect if only one sibling's exposure affects the other's outcome, and it identifies the difference between the spillover effects if both siblings' exposures affect the others' outcomes. The method fails with outcome-to-exposure spillover or with outcome-to-outcome spillover. Analytic results, Monte Carlo simulations, and a brief application demonstrate the method and its limitations.
RESULTS
We estimate the spillover effect of a child's preterm birth on an older sibling's literacy skills, measured by the Phonological Awareness Literacy Screening-Kindergarten test. We analyze 20,010 sibling pairs from a population-wide, Wisconsin-based (United States) birth cohort. Without covariate adjustment, we estimate that preterm birth modestly decreases an older sibling's test score.
CONCLUSIONS
Gain-scores are a promising strategy for identifying exposure-to-outcome spillover effects in sibling pairs while controlling for sibling-invariant unobserved confounding.
Topics: Child; Humans; Infant, Newborn; Premature Birth; Regression Analysis; Research Design; Siblings; United States; Wisconsin
PubMed: 34990828
DOI: 10.1016/j.annepidem.2021.12.010