John D. Storey proposes a new approach to multiple-hypothesis testing, focusing on controlling the false discovery rate (FDR) and the positive false discovery rate (pFDR). Unlike traditional methods that fix the error rate and estimate the rejection region, Storey's approach fixes the rejection region and estimates the corresponding error rate. This method is argued to be more applicable, accurate, and powerful. The paper introduces the pFDR, which is a more appropriate measure of error compared to FDR, and discusses the calculation of the q-value, a pFDR analogue of the p-value. Numerical results show that the proposed method can increase power by over 800% compared to the Benjamini-Hochberg FDR method. Theoretical results support the proposed approach, showing that it provides conservative estimates of pFDR and FDR. The paper also discusses the calculation of the optimal tuning parameter and the application of the method in various scenarios, including data mining.John D. Storey proposes a new approach to multiple-hypothesis testing, focusing on controlling the false discovery rate (FDR) and the positive false discovery rate (pFDR). Unlike traditional methods that fix the error rate and estimate the rejection region, Storey's approach fixes the rejection region and estimates the corresponding error rate. This method is argued to be more applicable, accurate, and powerful. The paper introduces the pFDR, which is a more appropriate measure of error compared to FDR, and discusses the calculation of the q-value, a pFDR analogue of the p-value. Numerical results show that the proposed method can increase power by over 800% compared to the Benjamini-Hochberg FDR method. Theoretical results support the proposed approach, showing that it provides conservative estimates of pFDR and FDR. The paper also discusses the calculation of the optimal tuning parameter and the application of the method in various scenarios, including data mining.