基于错误发现率(FDR:False Discovery Rate)的多重假设检验(MHT:Multiple Hypothesis Testing),已成为一种有效解决大规模统计推断问题的新方法。本文以错误控制为主线,对多重假设检验问题的错误控制理论、方法、过程和最新进展进行综述,并对多重假设检验方法在经济计量中的应用进行展望。
It is common in econometric applications that several hypothesis tests are carried out at the same time. The paper reviews the theory and procedures of multiple hypothesis testing ( MHT), summarizes the recent developments of false discovery rate and finally prospects the apphcation of MHT in econometrics.