Search tips
Search criteria

Results 1-4 (4)

Clipboard (0)

Select a Filter Below

more »
Year of Publication
Document Types
1.  The Combination of Ecological and Case-Control Data 
Ecological studies, in which data are available at the level of the group, rather than at the level of the individual, are susceptible to a range of biases due to their inability to characterize within-group variability in exposures and confounders. In order to overcome these biases, we propose a hybrid design in which ecological data are supplemented with a sample of individual-level case-control data. We develop the likelihood for this design and illustrate its benefits via simulation, both in bias reduction when compared to an ecological study, and in efficiency gains relative to a conventional case-control study. An interesting special case of the proposed design is the situation where ecological data are supplemented with case-only data. The design is illustrated using a dataset of county-specific lung cancer mortality rates in the state of Ohio from 1988.
PMCID: PMC2802495  PMID: 20057922
Ecological bias; Efficiency; Outcome-dependent sampling; Two-phase sampling; Within-area confounding
2.  On the Assessment of Monte Carlo Error in Simulation-Based Statistical Analyses 
The American statistician  2009;63(2):155-162.
Statistical experiments, more commonly referred to as Monte Carlo or simulation studies, are used to study the behavior of statistical methods and measures under controlled situations. Whereas recent computing and methodological advances have permitted increased efficiency in the simulation process, known as variance reduction, such experiments remain limited by their finite nature and hence are subject to uncertainty; when a simulation is run more than once, different results are obtained. However, virtually no emphasis has been placed on reporting the uncertainty, referred to here as Monte Carlo error, associated with simulation results in the published literature, or on justifying the number of replications used. These deserve broader consideration. Here we present a series of simple and practical methods for estimating Monte Carlo error as well as determining the number of replications required to achieve a desired level of accuracy. The issues and methods are demonstrated with two simple examples, one evaluating operating characteristics of the maximum likelihood estimator for the parameters in logistic regression and the other in the context of using the bootstrap to obtain 95% confidence intervals. The results suggest that in many settings, Monte Carlo error may be more substantial than traditionally thought.
PMCID: PMC3337209  PMID: 22544972
Bootstrap; Jackknife; Replication
3.  Statistical Approaches for Modeling Radiologists’ Interpretive Performance 
Academic radiology  2009;16(2):227-238.
Although much research has been conducted to understand the influence of interpretive volume on radiologists’ performance of mammography interpretation, the published literature has been unable to achieve consensus on the volume standards required for optimal mammography accuracy. One potential contributing factor is that studies have used different statistical approaches to address the same underlying scientific question. Such studies rely on multiple mammography interpretations from a sample of radiologists; thus, an important statistical issue is appropriately accounting for dependence, or correlation, among interpretations made by (or clustered within) the same radiologist. This manuscript aims to increase awareness about differences between statistical approaches used to analyze clustered data. We review statistical frameworks commonly used to model binary measures of interpretive performance, focusing on two broad classes of regression frameworks: marginal and conditional models. While both frameworks account for dependence in clustered data, the interpretations of their parameters differ; hence, the choice of statistical framework may (implicitly) dictate the scientific question being addressed. Additional statistical issues that influence estimation and inference are also discussed, together with their potential impact on the scientific interpretation of the analysis. This work was motivated by ongoing research being conducted by the Breast Cancer Surveillance Consortium; however, the ideas are relevant to a broad range of settings where researchers seek to identify and understand sources of variability in clustered binary outcomes.
PMCID: PMC2653267  PMID: 19124109
clustered data analysis; generalized estimating equations; generalized linear mixed models; random effect; hierarchical; mammography performance; interpretive volume
4.  An Assessment of the Quality of Mammography Care at Facilities Treating Medically Vulnerable Populations 
Medical care  2008;46(7):701-708.
Women in medically vulnerable populations, including racial and ethnic minorities, the socioeconomically disadvantaged, and residents of rural areas, experience higher breast cancer mortality than do others. Whether mammography facilities that treat vulnerable women demonstrate lower quality of care than other facilities is unknown.
To assess the quality of mammography women receive at facilities characterized as serving a high proportion of medically vulnerable populations.
Research Design
We prospectively collected self-reported breast cancer risk factor information, mammography interpretations, and cancer outcomes on 1,579,929 screening mammography examinations from 750,857 women, aged 40–80 years, attending any of 151 facilities in the Breast Cancer Surveillance Consortium, between 1998 and 2004. To classify facilities as serving medically vulnerable populations, we used 4 criteria: educational attainment, racial/ethnic minority, household income, and rural/urban residence.
After adjustment for patient-level factors known to effect mammography accuracy, facilities serving vulnerable populations had significantly higher mammography specificity than did other facilities: ie, those serving women who were minorities [odds ratio (OR): 1.32; 95% confidence interval (CI): 1.01–1.73], living in rural areas (1.45; 1.15–1.73), and with lower household income (1.33; 1.05–1.68). We observed no statistically significant differences between facilities in mammography sensitivity.
Facilities serving high proportions of vulnerable populations provide screening mammography with equal or better quality (as reflected in higher specificity with no corresponding decrease in sensitivity) than other facilities. Further research is needed to understand the mechanisms underlying these findings.
PMCID: PMC2674332  PMID: 18580389
mammography; screening; quality of care; vulnerable populations

Results 1-4 (4)