Receiver operating characteristic (ROC) curves have been widely used in medical research to evaluate the accuracy of diagnostic tests. ROC curves are useful in illustrating the ability of a biomarker to differentiate between diseased and non-diseased groups. There have been much work developed in non-parametric, semi-parametric and parametric approaches for ROC curve estimation to address issues surrounding matched and unmatched case control designs as well as designs that give rise to correlated biomarkers. This paper reviews some developed methods to estimate ROC curves for matched and unmatched case control designs. The parametric, semi-parametric and non-parametric methods to estimate ROC curves are demonstrated and the gaps and limitations of methods presented are discussed.

biomarker, ROC curve, matched case-control design.