Abstract
The two-phase design has recently received attention in the statistical literature as an extension to the traditional case-control study for settings where a predictor of interest is rare or subject to missclassification. Despite a thorough methodological treatment and the potential for substantial efficiency gains, the two-phase design has not been widely adopted. This may be due, in part, to a lack of general-purpose, readily-available software. The osDesign package for R provides a suite of functions for analyzing data from a two-phase and/or case-control design, as well as evaluating operating characteristics, including bias, efficiency and power. The evaluation is simulation-based, permitting flexible application of the package to a broad range of scientific settings. Using lung cancer mortality data from Ohio, the package is illustrated with a detailed case-study in which two statistical goals are considered: (i) the evaluation of small-sample operating characteristics for two-phase and case-control designs and (ii) the planning and design of a future two-phase study.
Highlights
Researchers have at their disposal a wide variety of study designs with which to identify and assess associations between predictors and outcomes
At least for these examples, power gains under a two-phase design are primarily obtained for the coefficient corresponding to the covariate that is stratified upon
The two-phase design is well-established in the statistical literature, researchers have been slow to adopt the design as an efficient alternative to the traditional case-control design
Summary
Researchers have at their disposal a wide variety of study designs with which to identify and assess associations between predictors and outcomes. For the setting where the exposure is binary, White (1982) proposed using the two-phase design as a means to improving efficiency (Neyman 1938) In this context, the design stratifies the population jointly on the outcome and exposure, resulting in four phase I strata. In this article we introduce and provide an overview of a new R (R Development Core Team 2011) package, osDesign, that contains a suite of functions useful when designing and analyzing two-phase and case-control studies.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have