| as_eval |
Build an Evaluation Object |
| ev_bootstrap |
Cluster Bootstrap for an Arbitrary Statistic |
| ev_cluster |
Cluster-Robust Standard Error for an Evaluation |
| ev_elo |
Bradley-Terry Ratings from Pairwise Preferences |
| ev_icc |
Intra-Cluster Correlation |
| ev_judge_agreement |
Agreement Between a Model Judge and a Human Gold Standard |
| ev_judge_debias |
Debias a Model Judge with a Small Human Sample |
| ev_judge_power |
How Many Human Labels a Debiased Evaluation Needs |
| ev_mde |
Smallest Difference an Evaluation Can Detect |
| ev_multi |
Multiplicity Adjustment Across a Benchmark Suite |
| ev_paired |
Paired Comparison of Two Models |
| ev_plot |
Plot Results with Error Bars |
| ev_power |
Number of Questions Needed to Detect a Difference |
| ev_rank |
Bootstrap Rank Intervals for a Leaderboard |
| ev_resample |
Variance Decomposition for Repeated Sampling |
| ev_score |
Evaluation Score with a Standard Error |
| ev_table |
Collect Results into a Table |
| ev_unpaired |
Unpaired Comparison of Two Models |
| ev_variance_reduction |
Variance Reduction with a Reference Model |
![[R logo]](../../../doc/html/Rlogo.svg)
![[Up]](../../../doc/html/left.jpg)
![[Top]](../../../doc/html/up.jpg)