Commonly 1-4 controls are selected for each case. Since the covariate is not measured for all participants, the nested case control model is both less expensive and lessmore(?) efficient than a full-cohort analysis. However, it has been shown that with 4 controls per case and/or stratified sampling of controls, relatively little efficiency may be lost, depending on the method of estimation used.<ref name=Cai>{{cite journal |last=Cai |first=Tianxi |last2=Zheng |first2=Yingye |year=2012 |title=Evaluating prognostic accuracy of biomarkers in nested case–control studies |journal=Biostatistics |volume=13 |issue=1 |pages=89–100 |doi=10.1093/biostatistics/kxr021 }}</ref><ref>{{cite journal |last=Goldstein |first=Larry |last2=Zhang |first2=Haimeng |year=2009 |title=Efficiency of the maximum partial likelihood estimator for nested case control sampling |journal=Bernoulli |volume=15 |issue=2 |pages=569–597 |jstor=20680165 }}</ref>
