Lai Dejian, King Terri M, Moyé Lemuel A, Wei Qingyi
Program in Biometry, The University of Texas, School of Public Health, Houston 77030, USA.
Ann Epidemiol. 2003 Mar;13(3):204-8. doi: 10.1016/s1047-2797(02)00261-2.
In molecular epidemiologic studies, optimizing the use of available biological specimens while minimizing the cost is always a challenge. This is particularly true in pilot studies, which often have limited funding and involve small numbers of biological samples too small for assessment of recently developed biomarkers.
In this study we examined several statistical approaches for determining how many experimental subjects to use in a biomarker study and how many repeated measurements to make on each sample, given specific funding considerations and the correlated nature of the repeated measurements.
A molecular epidemiology study of DNA repair and aging in basal cell carcinoma was used to illustrate the application of the statistical methods proposed.
Our methods extend traditional designs on biomarker studies with repeated measurements to including funding constraints.
在分子流行病学研究中，在将可用生物样本的使用最优化的同时尽量降低成本始终是一项挑战。在试点研究中尤其如此，这类研究往往资金有限，涉及的生物样本数量过少，无法对最近开发的生物标志物进行评估。
在本研究中，我们考察了几种统计方法，用于确定在特定资金考量以及重复测量具有相关性的情况下，生物标志物研究中应使用多少实验对象以及对每个样本进行多少次重复测量。
一项关于基底细胞癌中DNA修复与衰老的分子流行病学研究被用于说明所提出的统计方法的应用。
我们的方法将传统的带有重复测量的生物标志物研究设计扩展到了包含资金限制的情况。
