Back to Search-quality version diff: v1.1.0 → v1.2.0 (canonical-lookup-V2 (independent corpus))
Search-quality version diff: v1.1.0 → v1.2.0 (canonical-lookup-V2 (independent corpus))

Paired Statistical Tests

Paired Wilcoxon signed-rank on per-query RR (B vs A):

  • N_nonzero = 10
  • W+ = 50.00, W− = 5.00
  • Two-sided p = 0.021824
  • One-sided p (v1.2.0 > v1.1.0) = 0.010912

McNemar on rank-1 outcome:

v1.2.0 rank-1v1.2.0 not rank-1
v1.1.0 rank-120 (concordant +)1 (regression)
v1.1.0 not rank-18 (improvement)1 (concordant −)
  • McNemar exact (binomial), two-sided p = 0.039062