To How Many Simultaneous Hypothesis Tests Can Normal, Student's t or Bootstrap Calibration Be Applied?

摘要: In the analysis of microarray data, and in some other contemporary statistical problems, it is not uncommon to apply hypothesis tests a highly simultaneous way. The number, N say, used can be much larger than sample sizes, n, which are applied, yet we wish calibrate so that overall level test accurate. Often sampling distribution quite different for each test, there may an opportunity combine data across samples. this setting, how large be, as function before accuracy becomes poor? Here answer question cases where statistic under Student's t type. We show if either normal or Student calibration, then accurate provided log increases at strictly slower rate n 1/3 diverges. On hand, bootstrap methods choose almost as...