FDR
False Discovery Rate, a standard statistical method for controlling the proportion of false positives in multiple hypothesis testing. In the Learn Then Test framework it is used to select in one pass a set of thresholds that satisfy the risk budget.
Timeline (last 90 days)
Conformal Policy Selection reformulates selective deployment as a multiple testing problem, using false discovery rate (FDR) control to provide statistical guarantees for individual-level AI deployment decisions.
The false discovery rate (FDR) is a statistical metric in multiple hypothesis testing that controls the proportion of false rejections, defined as the expected value of the proportion of rejected null hypotheses that are actually true.
The false discovery rate (FDR) was proposed by Benjamini and Hochberg in 1995 and is defined as the expected proportion of false discoveries among all findings judged to be significant.
The knockoff method constructs a counterfeit variable for each original variable and requires the two to satisfy exchange symmetry in the joint distribution, thereby using the difference in statistics between original variables and knockoffs to control the FDR; column-permutation equivariance is a key prerequisite for constructing valid knockoff statistics.
All Facts (4)
Conformal Policy Selection reformulates selective deployment as a multiple testing problem, using false discovery rate (FDR) control to provide statistical guarantees for individual-level AI deployment decisions.
50%UnverifiedThe false discovery rate (FDR) is a statistical metric in multiple hypothesis testing that controls the proportion of false rejections, defined as the expected value of the proportion of rejected null hypotheses that are actually true.
50%UnverifiedThe false discovery rate (FDR) was proposed by Benjamini and Hochberg in 1995 and is defined as the expected proportion of false discoveries among all findings judged to be significant.
50%UnverifiedThe knockoff method constructs a counterfeit variable for each original variable and requires the two to satisfy exchange symmetry in the joint distribution, thereby using the difference in statistics between original variables and knockoffs to control the FDR; column-permutation equivariance is a key prerequisite for constructing valid knockoff statistics.
50%