Epidemiologic Perspectives & Innovations - Latest Articles

Fitting additive Poisson models

Hendriek Boshuizen — 2010-07-20T00:00:00Z

This paper describes how to fit an additive Poisson model using standard software. It is illustrated with SAS code, but can be similarly used for other software packages.

Using variable importance measures from causal inference to rank risk factors of schistosomiasis infection in a rural setting in China

Sylvia Sudat — 2010-07-14T00:00:00Z

Background: Schistosomiasis infection, contracted through contact with contaminated water, is a global public health concern. In this paper we analyze data from a retrospective study reporting water contact and schistosomiasis infection status among 1011 individuals in rural China. We present semi-parametric methods for identifying risk factors through a comparison of three analysis approaches: a prediction-focused machine learning algorithm, a simple main-effects multivariable regression, and a semi-parametric variable importance (VI) estimate inspired by a causal population intervention parameter. Results: The multivariable regression found only tool washing to be associated with the outcome, with a relative risk of 1.03 and a 95% confidence interval (CI) of 1.01-1.05. Three types of water contact were found to be associated with the outcome in the semi-parametric VI analysis: July water contact (VI estimate 0.16, 95% CI 0.11-0.22), water contact from tool washing (VI estimate 0.88, 95% CI 0.80-0.97), and water contact from rice planting (VI estimate 0.71, 95% CI 0.53-0.96). The July VI result, in particular, indicated a strong association with infection status - its causal interpretation implies that eliminating water contact in July would reduce the prevalence of schistosomiasis in our study population by 84%, or from 0.3 to 0.05 (95% CI 78%-89%). Conclusions: The July VI estimate suggests possible within-season variability in schistosomiasis infection risk, an association not detected by the regression analysis. Though there are many limitations to this study that temper the potential for causal interpretations, if a high-risk time period could be detected in something close to real time, new prevention options would be opened. Most importantly, we emphasize that traditional regression approaches are usually based on arbitrary pre-specified models, making their parameters difficult to interpret in the context of real-world applications. Our results support the practical application of analysis approaches that, in contrast, do not require arbitrary model pre-specification, estimate parameters that have simple public health interpretations, and apply inference that considers model selection as a source of variation.

Can we use biomarkers in combination with self-reports to strengthen the analysis of nutritional epidemiologic studies?

Laurence Freedman — 2010-01-20T00:00:00Z

Identifying diet-disease relationships in nutritional cohort studies is plagued by the measurement error in self-reported intakes.The authors propose using biomarkers known to be correlated with dietary intake, so as to strengthen analyses of diet-disease hypotheses. The authors consider combining self-reported intakes and biomarker levels using principal components, Howe's method, or a joint statistical test of effects in a bivariate model. They compared the statistical power of these methods with that of conventional univariate analyses of self-reported intake or of biomarker level. They used computer simulation of different disease risk models, with input parameters based on data from the literature on the relationship between lutein intake and age-related macular degeneration.The results showed that if the dietary effect on disease was fully mediated through the biomarker level, then the univariate analysis of the biomarker was the most powerful approach. However, combination methods, particularly principal components and Howe's method, were not greatly inferior in this situation, and were as good as, or better than, univariate biomarker analysis if mediation was only partial or non-existent. In some circumstances sample size requirements were reduced to 20-50% of those required for conventional analyses of self-reported intake.The authors conclude that (i) including biomarker data in addition to the usual dietary data in a cohort could greatly strengthen the investigation of diet-disease relationships, and (ii) when the extent of mediation through the biomarker is unknown, use of principal components or Howe's method appears a good strategy.

A method to predict breast cancer stage using Medicare claims

Grace Smith — 2010-01-15T00:00:00Z

Background: In epidemiologic studies, cancer stage is an important predictor of outcomes. However, cancer stage is typically unavailable in medical insurance claims datasets, thus limiting the usefulness of such data for epidemiologic studies. Therefore, we sought to develop an algorithm to predict cancer stage based on covariates available from claims-based data. Methods: We identified a cohort of 77,306 women age ≥ 66 years with stage I-IV breast cancer, using the Surveillence Epidemiology and End Results (SEER)-Medicare database. We formulated an algorithm to predict cancer stage using covariates (demographic, tumor, and treatment characteristics) obtained from claims. Logistic regression models derived prediction equations in a training set, and equations' test characteristics (sensitivity, specificity, positive predictive value (PPV), and negative predictive value [NPV]) were calculated in a validation set. Results: Of the entire sample of women diagnosed with invasive breast cancer, 51% had stage I; 26% stage II; 11% stage III; and 4% stage IV disease. The equation predicting stage IV disease achieved sensitivity of 81%, specificity 89%, positive predictive value (PPV) 24%, and negative predictive value (NPV) 99%, while the equation distinguishing stage I/II from stage III disease achieved sensitivity 83%, specificity 78%, PPV 98%, and NPV 31%. Combined, the equations most accurately identified early stage disease and ascertained a sample in which 98% of patients were stage I or II. Conclusions: A claims-based algorithm was utilized to predict breast cancer stage, and was particularly successful when used to identify early stage disease. These prediction equations may be applied in future studies of breast cancer patients, substantially improving the utility of claims-based studies in this group. This method may similarly be employed to develop algorithms permitting claims-based epidemiologic studies of patients with other cancers.

Covariate balance in a Bayesian propensity score analysis of beta blocker therapy in heart failure patients

Lawrence McCandless — 2009-09-10T00:00:00Z

Regression adjustment for the propensity score is a statistical method that reduces confounding from measured variables in observational data. A Bayesian propensity score analysis extends this idea by using simultaneous estimation of the propensity scores and the treatment effect. In this article, we conduct an empirical investigation of the performance of Bayesian propensity scores in the context of an observational study of the effectiveness of beta-blocker therapy in heart failure patients. We study the balancing properties of the estimated propensity scores. Traditional Frequentist propensity scores focus attention on balancing covariates that are strongly associated with treatment. In contrast, we demonstrate that Bayesian propensity scores can be used to balance the association between covariates and the outcome. This balancing property has the effect of reducing confounding bias because it reduces the degree to which covariates are outcome risk factors.

Identifiability, exchangeability and confounding revisited

Sander Greenland — 2009-09-04T00:00:00Z

In 1986 the International Journal of Epidemiology published "Identifiability, Exchangeability and Epidemiological Confounding". We review the article from the perspective of a quarter century after it was first drafted and relate it to subsequent developments on confounding, ignorability, and collapsibility.

Update: Greenland and Robins (1986). Identifiability, exchangeability and epidemiological confounding.

George Maldonado — 2009-09-04T00:00:00Z

We are pleased to publish an update to "Identifiabiliity, exchangeability and epidemiological confounding" (IEEC) by Sander Greenland and James Robins, originally published in 1986 in the International Journal of Epidemiology. This is the first in a series of updates to classic epidemiologic-methods papers that EP&I has commissioned.

The role of causal criteria in causal inferences: Bradford Hill's "aspects of association"

Andrew Ward — 2009-06-17T00:00:00Z

As noted by Wesley Salmon and many others, causal concepts are ubiquitous in every branch of theoretical science, in the practical disciplines and in everyday life. In the theoretical and practical sciences especially, people often base claims about causal relations on applications of statistical methods to data. However, the source and type of data place important constraints on the choice of statistical methods as well as on the warrant attributed to the causal claims based on the use of such methods. For example, much of the data used by people interested in making causal claims come from non-experimental, observational studies in which random allocations to treatment and control groups are not present. Thus, one of the most important problems in the social and health sciences concerns making justified causal inferences using non-experimental, observational data. In this paper, I examine one method of justifying such inferences that is especially widespread in epidemiology and the health sciences generally – the use of causal criteria. I argue that while the use of causal criteria is not appropriate for either deductive or inductive inferences, they do have an important role to play in inferences to the best explanation. As such, causal criteria, exemplified by what Bradford Hill referred to as "aspects of [statistical] associations", have an indispensible part to play in the goal of making justified causal claims.

Trend tests for the evaluation of exposure-response relationships in epidemiological exposure studies

Ludwig Hothorn — 2009-03-06T00:00:00Z

One possibility for the statistical evaluation of trends in epidemiological exposure studies is the use of a trend test for data organized in a 2 × k contingency table. Commonly, the exposure data are naturally grouped or continuous exposure data are appropriately categorized. The trend test should be sensitive to any shape of the exposure-response relationship. Commonly, a global trend test only determines whether there is a trend or not. Once a trend is seen it is important to identify the likely shape of the exposure-response relationship. This paper introduces a best contrast approach and an alternative approach based on order-restricted information criteria for the model selection of a particular exposure-response relationship. For the simple change point alternative H1 : π1 = ...= πq <πq+1 = ... = πk an appropriate approach for the identification of a global trend as well as for the most likely shape of that exposure-response relationship is characterized by simulation and demonstrated for real data examples. Power and simultaneous confidence intervals can be estimated as well. If the conditions are fulfilled to transform the exposure-response data into a 2 × k table, a simple approach for identification of a global trend and its elementary shape is available for epidemiologists.

Using the National Health Interview Survey to understand and address the impact of tobacco in the United States: past perspectives and future considerations

Cathy Backinger — 2008-12-04T00:00:00Z

ObjectiveThe National Health Interview Survey (NHIS) is a continuous, nationwide, household interview survey of the civilian noninstitutionalized population of the United States. This annual survey is conducted by the National Center for Health Statistics, part of the Centers for Disease Control and Prevention. Since 1965, the survey and its supplements have provided data on issues related to the use of cigarettes and other tobacco products. This paper describes the survey, provides an overview of peer-reviewed and government-issued research that uses tobacco-related data from the NHIS, and suggests additional areas for exploration and directions for future research.Data sourcesWe performed literature searches using the PubMed database, selecting articles from 1966 to 2008. Study selection. Inclusion criteria were relevancy to tobacco research and primary use of NHIS data; 117 articles met these criteria. Data extraction and synthesis. Tobacco-related data from the NHIS have been used to analyze smoking prevalence and trends; attitudes, knowledge, and beliefs; initiation; cessation and advice to quit; health care practices; health consequences; secondhand smoke exposure; and use of smokeless tobacco. To date, use of these data has had broad application; however, great potential still exists for additional use. Conclusion: NHIS data provide information that can be useful to both practitioners and researchers. It is important to explore new and creative ways to best use these data and to address the full range of salient tobacco-related topics. Doing so will better inform future tobacco control research and programs.