Prospective Analysis of Logistic Case-Control Studies

Carroll, R. J.; Wang, Suojin; Wang, C. Y.

doi:10.2307/2291139

Cited by 42 publications

(56 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The distributions of fasting triglycerides, ACR, and fasting insulin were log transformed (natural log) before analysis to approximate more normal distributions. General linear models (28) or logistic regression techniques (29) were used to compare the adjusted differences between case subjects and control subjects. Likelihood ratio tests were performed to determine statistical interactions between sex and case-control status by comparing the log likelihood between the two nested models, one with only the main effects and the other with both the main effects and the interaction terms in the model.…”

Section: Statistical Proceduresmentioning

confidence: 99%

Sex Differences in Endothelial Function Markers Before Conversion to Pre-Diabetes: Does the Clock Start Ticking Earlier Among Women?

et al. 2007

View full text Add to dashboard Cite

OBJECTIVE -We examined whether biomarkers of endothelial function, fibrinolysis/ thrombosis and adiponectin, predict the progression from normal to pre-diabetes more strongly among women than men over 6 years of follow-up from the Western New York Health Study. participants from the Western New York Health Study, who were free of type 2 diabetes and cardiovascular disease at baseline (1996 -2001), were selected for reexamination. An incident case of pre-diabetes was defined as fasting glucose Ͻ100 mg/dl at the baseline examination and Ն100 and Ͻ126 mg/dl at the follow-up examination. Biomarkers of endothelial function (E-selectin and soluble intracellular adhesion molecule-1 [sICAM-1]), fibrinolysis/thrombosis (plasminogen activator inhibitor-1 [PAI-1]), and fasting insulin, adiponectin, and inflammation (high-sensitivity C-reactive protein) were measured in frozen (Ϫ190°C) baseline samples. RESEARCH DESIGN AND METHODSRESULTS -Multivariate analyses revealed higher adjusted mean values of biomarkers of endothelial dysfunction (E-selectin and sICAM-1) and fibrinolysis (PAI-1) and lower mean values of adiponectin only among women who developed pre-diabetes compared with control subjects. Formal tests for interaction between sex and case/control status were statistically significant for E-selectin (P ϭ 0.042), PAI-1 (P ϭ 0.001), sICAM-1 (P ϭ 0.011), and frequency of hypertension (P Ͻ 0.001).CONCLUSIONS -These results support the concept that women who progressed from normoglycemia to pre-diabetes have greater endothelial dysfunction than men as well as more hypertension and a greater degree of fibrinolysis/thrombosis. Whether this relates to the higher risk of heart disease among diabetic women awaits further study. Diabetes Care 30:354 -359, 2007D eath rates from coronary heart disease (CHD) in the U.S. have fallen dramatically over the last several decades; however, the rate of decline has been greater among men than among women (1). The factors underlying this sex difference are unclear (2-6). It has also been suggested that women, especially those with type 2 diabetes, are more likely to have coronary microvascular disease than men (7,8). It is well known that diabetic women have a much higher risk for CHD than their male counterparts, a risk not completely explained by traditional biological and psychosocial factors (9,10).Previous studies have shown that the frequency of nonfatal myocardial infarction is increased before the clinical diagnosis of type 2 diabetes (11) and that women with impaired glucose tolerance tend to have a more atherogenic risk profile than their male counterparts years before the diagnosis of clinical diabetes (12). This observation has led to the "ticking clock" hypothesis (13), wherein the elevated CHD risk among diabetic individuals may be due more to their longstanding atherogenic risk profile than to hyperglycemia per se, which is more strongly associated with the risk of microvascular events (14). Recently, attention has been focused on the role of emerging risk factors including ...

show abstract

Section: Statistical Proceduresmentioning

confidence: 99%

Sex Differences in Endothelial Function Markers Before Conversion to Pre-Diabetes: Does the Clock Start Ticking Earlier Among Women?

et al. 2007

View full text Add to dashboard Cite

show abstract

“…However, this result holds only under the assumption that one can assume a saturated non-parametric distribution for the exposure. Carroll et al [1995] showed that a prospective analysis of retrospectively ascertained data may be less efficient than a retrospective analysis when one restricts the exposure distribution in some fashion.…”

Section: Introductionmentioning

confidence: 99%

“…Translating the results of Carroll et al [1995] to the haplotype-analysis situation, prospective methods are likely less efficient than retrospective methods when one places a restriction on the possible distribution of haplotypes. The assumption of Hardy-Weinberg Equilibrium (HWE) of sample haplotype frequencies is such a restriction on the haplotype distribution.…”

Section: Introductionmentioning

confidence: 99%

Comparison of prospective and retrospective methods for haplotype inference in case‐control studies

Satten

Epstein

2004

Genetic Epidemiology

112

View full text Add to dashboard Cite

We compare bias and power of three methods for haplotype inference on disease risk using unphased genotype data from a case-control study. We examine the prospective score test of Schaid et al., a novel modification of the prospective estimating equations of Zhao et al. and the retrospective likelihood of Epstein and Satten. We find that all three approaches are roughly comparable when the haplotype effect on disease odds follows a multiplicative model. However, for dominant and recessive models of haplotype effect, the retrospective-likelihood method has increased efficiency with respect to the prospective methods. As all three methods assume haplotype frequencies are in Hardy-Weinberg Equilibrium (HWE), we compare the robustness of each procedure to departures from HWE. We find the prospective methods are robust to departure from HWE, while the retrospective-likelihood method is biased for dominant and recessive models of haplotype effect. To remedy this limitation of the retrospective-likelihood method, we propose a modification that allows for a non-negative fixation index (common to all haplotype pairs) and show it dramatically reduces the bias of the retrospective likelihood when HWE is violated.

show abstract

“…We assume logit( (D i | X i )) = 0 + 1 (X i ) = 0 + 11 X 1i + \1 X \1i (1) for i = 1; : : : ; N and some constants 0 and 1 . We use to denote the parameters 0 , 1 collectively, 11 to denote the ÿrst element of 1 and \1 to denote the remaining S − 1 elements. The baseline prevalence of disease is denoted (D i | X 0 ) where X 0 takes reference values for all variables within X .…”

Section: Without Misclassiÿcationmentioning

confidence: 99%

A Bayesian approach to prospective binary outcome studies with misclassification in a binary risk factor

Prescott

Garthwaite

2005

Statist. Med.

View full text Add to dashboard Cite

Misclassification in a binary exposure variable within an unmatched prospective study may lead to a biased estimate of the disease-exposure relationship. It usually gives falsely small credible intervals because uncertainty in the recorded exposure is not taken into account. When there are several other perfectly measured covariates, interrelationships may introduce further potential for bias. Bayesian methods are proposed for analysing binary outcome studies in which an exposure variable is sometimes misclassified, but its correct values have been validated for a random subsample of the subjects. This Bayesian approach can model relationships between explanatory variables and between exploratory variables and the probabilities of misclassification. Three logistic regressions are used to relate disease to true exposure, misclassified exposure to true exposure and true exposure to other covariates. Credible intervals may be used to make decisions about whether certain parameters are unnecessary and hence whether the model can be reduced in complexity. In the disease-exposure model, for parameters representing coefficients related to perfectly measured covariates, the precision of posterior estimates is only slightly lower than would be found from data with no misclassification. For the risk factor which has misclassification, the estimates of model coefficients obtained are much less biased than those with misclassification ignored.

show abstract

Prospective Analysis of Logistic Case-Control Studies

Cited by 42 publications

References 0 publications

Sex Differences in Endothelial Function Markers Before Conversion to Pre-Diabetes: Does the Clock Start Ticking Earlier Among Women?

Sex Differences in Endothelial Function Markers Before Conversion to Pre-Diabetes: Does the Clock Start Ticking Earlier Among Women?

Comparison of prospective and retrospective methods for haplotype inference in case‐control studies

A Bayesian approach to prospective binary outcome studies with misclassification in a binary risk factor

Contact Info

Product

Resources

About