诊断试验ROC参数估计双正态样本量估计方法探讨  

Study of the Sample Size Determination for Diagnostic Accuracy Studies Involving Binormal ROC Parameter Estimation

作　　者：谷红梅[1] 李康[1] 

机构地区：[1]哈尔滨医科大学卫生统计学教研室,150001

出　　处：《中国卫生统计》2006年第1期2-4,共3页Chinese Journal of Health Statistics

基　　金：国家自然科学基金资助项目(项目编号:30371253)

摘　　要：目的探讨ROC双正态样本量估计方法的准确性。方法通过Monte Carlo方法对ROC双正态样本量估计法进行评价与修正。结果根据模拟试验结果得到双正态样本量估计法的校正公式及修正曲线。结论采用文中给出的样本量调整方法,可以有效地进行样本量估计,达到诊断试验评价的要求。Objective Discuss the accuracy of sample size determination involving binormal ROC parameter estimation. Methods We conducted a Monte Carlo simulation study to evaluate and adjust the accuracy of the sample size determination. Results Obtain the adjusted formula and curve of the sample size. Conclusion The method mentioned in this article is effective to determine the sample size which is satisfied the requirement of the assessment of diagnostic test involving binormal ROC parameter estimation.

关 键 词：ROC分析 参数估计 双正态分布 样本含量 

分 类 号：R44[医药卫生—诊断学]