Logistic Regression Analysis and Efficient Design for Two-Stage Studies1

Kevin C. Cain; N. E. Breslow

doi:10.1093/oxfordjournals.aje.a115074

December 1, 1988American Journal of Epidemiology

Logistic Regression Analysis and Efficient Design for Two-Stage Studies1

View at Publisher

Ask AI

Bookmark

Share

Key Points

Develop and evaluate efficient statistical methods and sampling designs using logistic regression for two-stage epidemiologic studies.
Formulated logistic regression estimators tailored to two-stage designs where basic covariates are assessed in an initial large sample and costly exposures are measured in a subsample.
Derived optimal second-stage sampling fractions and variance estimators to maximize statistical efficiency under fixed budgetary or sample size constraints.
Balanced and optimal two-stage sampling allocations substantially reduce standard errors of odds ratio estimates relative to simple random subsampling.
Weighted logistic regression estimators correct for biased sampling fractions across strata while maintaining consistency and near-optimal asymptotic efficiency.

Implication

Methodological analysis reveals optimal logistic regression models in two-stage epidemiologic cohorts, indicating improved statistical efficiency at reduced research cost.

Abstract

Journal Article LOGISTIC REGRESSION ANALYSIS AND EFFICIENT DESIGN FOR TWO-STAGE STUDIES Get access KEVIN C. CAIN, KEVIN C. CAIN Search for other works by this author on: Oxford Academic PubMed Google Scholar NORMAN E. BRESLOW NORMAN E. BRESLOW Search for other works by this author on: Oxford Academic PubMed Google Scholar American Journal of Epidemiology, Volume 128, Issue 6, December 1988, Pages 1198–1206, https://doi.org/10.1093/oxfordjournals.aje.a115074 Published: 01 December 1988

Discussion

No takes yet. Share an insight, caveat, or question.

Cite This Study

Cain et al. (1988) studied this question.

synapsesocial.com/papers/6a174ee54c7f4e15c15df7d6 https://doi.org/10.1093/oxfordjournals.aje.a115074

View at Publisher

Ask AI

Bookmark

Share

Logistic Regression Analysis and Efficient Design for Two-Stage Studies1

Key Points

Implication

Abstract

Discussion

Cite This Study

Logistic Regression Analysis and Efficient Design for Two-Stage Studies1

Key Points

Implication

Abstract

Discussion

Cite This Study

Keep reading

Keep reading