Virtua Fighter 5 REVO · v1.10 · Character Matchup Winrates
Eileen vs Goh
Matches counted759
Win rate54.0%
Widest swing-6.7 pts
Survive correction0
Period2026/03/26 – 2026/09/23
Where it was fought
Eileen's win rate on each stage, against this matchup everywhere| Stage | Stage effect | Win % | Change | p | Matches |
|---|---|---|---|---|---|
| Fence and open | 60.0% | +6.0 | 0.435 | 40 · | |
| Single wall | 57.4% | +3.3 | 0.563 | 68 · | |
| Rectangle | 57.3% | +3.3 | 0.508 | 89 | |
| Breakable half fence | 55.3% | +1.3 | 0.802 | 85 | |
| Open | 54.4% | +0.4 | 0.931 | 90 | |
| Low fence | 54.0% | -0.1 | 0.990 | 76 · | |
| Full fence | 52.8% | -1.2 | 0.824 | 72 · | |
| Octagon | 52.3% | -1.7 | 0.772 | 65 · | |
| Half fence | 50.8% | -3.2 | 0.601 | 61 · | |
| Breakable full fence | 47.4% | -6.7 | 0.220 | 76 · |
p < 0.05 on its ownStill there after correcting for how many were tested
Stage against stage
Eileen's win rate on the row's stage, minus the same on the column'sAll ten shapes at once: chi-square 3.06 on 9 df, p 0.962
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 52.8%72 | +5.40.511 | +2.00.822 | -2.50.753 | -1.20.887 | -4.60.587 | -7.20.461 | -1.70.833 | -4.50.566 | +0.50.956 |
| Breakable full fence | -5.40.511 | 47.4%76 | -3.50.688 | -7.90.315 | -6.60.417 | -10.00.231 | -12.60.196 | -7.10.364 | -9.90.203 | -4.90.559 |
| Half fence | -2.00.822 | +3.50.688 | 50.8%61 | -4.50.593 | -3.10.716 | -6.50.457 | -9.20.365 | -3.60.661 | -6.50.433 | -1.50.867 |
| Breakable half fence | +2.50.753 | +7.90.315 | +4.50.593 | 55.3%85 | +1.30.864 | -2.10.799 | -4.70.620 | +0.80.910 | -2.00.789 | +3.00.716 |
| Low fence | +1.20.887 | +6.60.417 | +3.10.716 | -1.30.864 | 54.0%76 | -3.40.681 | -6.00.532 | -0.50.949 | -3.40.665 | +1.60.846 |
| Single wall | +4.60.587 | +10.00.231 | +6.50.457 | +2.10.799 | +3.40.681 | 57.4%68 | -2.60.788 | +2.90.716 | +0.10.995 | +5.00.559 |
| Fence and open | +7.20.461 | +12.60.196 | +9.20.365 | +4.70.620 | +6.00.532 | +2.60.788 | 60.0%40 | +5.60.556 | +2.70.774 | +7.70.441 |
| Open | +1.70.833 | +7.10.364 | +3.60.661 | -0.80.910 | +0.50.949 | -2.90.716 | -5.60.556 | 54.4%90 | -2.90.700 | +2.10.792 |
| Rectangle | +4.50.566 | +9.90.203 | +6.50.433 | +2.00.789 | +3.40.665 | -0.10.995 | -2.70.774 | +2.90.700 | 57.3%89 | +5.00.538 |
| Octagon | -0.50.956 | +4.90.559 | +1.50.867 | -3.00.716 | -1.60.846 | -5.00.559 | -7.70.441 | -2.10.792 | -5.00.538 | 52.3%65 |
Better on the row's stage — deeper at 5 and 10 pointsBetter on the column's stagep < 0.05 on its ownStill there after correcting for how many were tested· fewer than 80 decided matches on one side of the comparison
How significance is decided
- Each gap is two win rates compared with a pooled two-proportion z test, over decided matches only.
- The 95% interval is Newcombe's hybrid score method, which keeps its shape near 0% and 100% where a symmetric interval does not.
- q is p corrected for how many tests were asked at once, by Benjamini–Hochberg at a 5% false discovery rate. A figure is called real on q, never on p alone.
- Standard errors are widened by a measured design effect, because one player appears in many matches and those matches are not independent of each other.
- Stages are assigned at random, so a gap between them is the stage's own effect and not a difference in who chose to play where.
Matches counted634
Win rate56.3%
Widest swing-7.4 pts
Survive correction0
Period2026/03/26 – 2026/09/23
Where it was fought
Eileen's win rate on each stage, against this matchup everywhere| Stage | Stage effect | Win % | Change | p | Matches |
|---|---|---|---|---|---|
| Fence and open | 61.1% | +4.8 | 0.550 | 36 · | |
| Rectangle | 60.5% | +4.2 | 0.429 | 76 · | |
| Open | 58.6% | +2.3 | 0.686 | 70 · | |
| Single wall | 57.1% | +0.8 | 0.888 | 63 · | |
| Breakable half fence | 56.9% | +0.6 | 0.908 | 72 · | |
| Low fence | 56.9% | +0.6 | 0.916 | 65 · | |
| Octagon | 55.6% | -0.8 | 0.907 | 54 · | |
| Full fence | 55.0% | -1.3 | 0.830 | 60 · | |
| Breakable full fence | 50.0% | -6.3 | 0.283 | 64 · | |
| Half fence | 48.9% | -7.4 | 0.290 | 47 · |
p < 0.05 on its ownStill there after correcting for how many were tested
Stage against stage
Eileen's win rate on the row's stage, minus the same on the column'sAll ten shapes at once: chi-square 3.19 on 9 df, p 0.956
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 55.0%60 | +5.00.577 | +6.10.533 | -1.90.823 | -1.90.829 | -2.10.811 | -6.10.558 | -3.60.682 | -5.50.517 | -0.60.953 |
| Breakable full fence | -5.00.577 | 50.0%64 | +1.10.912 | -6.90.418 | -6.90.431 | -7.10.420 | -11.10.285 | -8.60.320 | -10.50.212 | -5.60.547 |
| Half fence | -6.10.533 | -1.10.912 | 48.9%47 | -8.00.392 | -8.00.403 | -8.20.393 | -12.20.270 | -9.60.305 | -11.60.208 | -6.60.506 |
| Breakable half fence | +1.90.823 | +6.90.418 | +8.00.392 | 56.9%72 | +0.00.998 | -0.20.981 | -4.20.679 | -1.60.844 | -3.60.658 | +1.40.876 |
| Low fence | +1.90.829 | +6.90.431 | +8.00.403 | -0.00.998 | 56.9%65 | -0.20.980 | -4.20.683 | -1.60.846 | -3.60.665 | +1.40.881 |
| Single wall | +2.10.811 | +7.10.420 | +8.20.393 | +0.20.981 | +0.20.980 | 57.1%63 | -4.00.700 | -1.40.868 | -3.40.686 | +1.60.863 |
| Fence and open | +6.10.558 | +11.10.285 | +12.20.270 | +4.20.679 | +4.20.683 | +4.00.700 | 61.1%36 | +2.50.801 | +0.60.953 | +5.50.601 |
| Open | +3.60.682 | +8.60.320 | +9.60.305 | +1.60.844 | +1.60.846 | +1.40.868 | -2.50.801 | 58.6%70 | -2.00.810 | +3.00.736 |
| Rectangle | +5.50.517 | +10.50.212 | +11.60.208 | +3.60.658 | +3.60.665 | +3.40.686 | -0.60.953 | +2.00.810 | 60.5%76 | +5.00.571 |
| Octagon | +0.60.953 | +5.60.547 | +6.60.506 | -1.40.876 | -1.40.881 | -1.60.863 | -5.50.601 | -3.00.736 | -5.00.571 | 55.6%54 |
Better on the row's stage — deeper at 5 and 10 pointsBetter on the column's stagep < 0.05 on its ownStill there after correcting for how many were tested· fewer than 80 decided matches on one side of the comparison
How significance is decided
- Each gap is two win rates compared with a pooled two-proportion z test, over decided matches only.
- The 95% interval is Newcombe's hybrid score method, which keeps its shape near 0% and 100% where a symmetric interval does not.
- q is p corrected for how many tests were asked at once, by Benjamini–Hochberg at a 5% false discovery rate. A figure is called real on q, never on p alone.
- Standard errors are widened by a measured design effect, because one player appears in many matches and those matches are not independent of each other.
- Stages are assigned at random, so a gap between them is the stage's own effect and not a difference in who chose to play where.
Matches counted125
Win rate42.4%
Widest swing17.6 pts
Survive correction0
Period2026/03/26 – 2026/09/23
Where it was fought
Eileen's win rate on each stage, against this matchup everywhere| Stage | Stage effect | Win % | Change | p | Matches |
|---|---|---|---|---|---|
| Single wall | 60.0% | +17.6 | 0.416 | 5 · | |
| Half fence | 57.1% | +14.7 | 0.236 | 14 · | |
| Fence and open | 50.0% | +7.6 | 0.755 | 4 · | |
| Breakable half fence | 46.1% | +3.8 | 0.772 | 13 · | |
| Full fence | 41.7% | -0.7 | 0.957 | 12 · | |
| Open | 40.0% | -2.4 | 0.813 | 20 · | |
| Rectangle | 38.5% | -3.9 | 0.761 | 13 · | |
| Low fence | 36.4% | -6.0 | 0.671 | 11 · | |
| Octagon | 36.4% | -6.0 | 0.671 | 11 · | |
| Breakable full fence | 33.3% | -9.1 | 0.504 | 12 · |
p < 0.05 on its ownStill there after correcting for how many were tested
Stage against stage
Eileen's win rate on the row's stage, minus the same on the column'sAll ten shapes at once: chi-square 2.91 on 9 df, p 0.968
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 41.7%12 | +8.30.673 | -15.50.431 | -4.50.821 | +5.30.795 | -18.30.490 | -8.30.771 | +1.70.926 | +3.20.870 | +5.30.795 |
| Breakable full fence | -8.30.673 | 33.3%12 | -23.80.225 | -12.80.513 | -3.00.879 | -26.70.309 | -16.70.551 | -6.70.706 | -5.10.790 | -3.00.879 |
| Half fence | +15.50.431 | +23.80.225 | 57.1%14 | +11.00.568 | +20.80.302 | -2.90.912 | +7.10.800 | +17.10.324 | +18.70.332 | +20.80.302 |
| Breakable half fence | +4.50.821 | +12.80.513 | -11.00.568 | 46.1%13 | +9.80.628 | -13.80.599 | -3.90.893 | +6.20.727 | +7.70.691 | +9.80.628 |
| Low fence | -5.30.795 | +3.00.879 | -20.80.302 | -9.80.628 | 36.4%11 | -23.60.377 | -13.60.634 | -3.60.842 | -2.10.916 | +0.01.000 |
| Single wall | +18.30.490 | +26.70.309 | +2.90.912 | +13.80.599 | +23.60.377 | 60.0%5 | +10.00.764 | +20.00.420 | +21.50.410 | +23.60.377 |
| Fence and open | +8.30.771 | +16.70.551 | -7.10.800 | +3.90.893 | +13.60.634 | -10.00.764 | 50.0%4 | +10.00.711 | +11.50.682 | +13.60.634 |
| Open | -1.70.926 | +6.70.706 | -17.10.324 | -6.20.727 | +3.60.842 | -20.00.420 | -10.00.711 | 40.0%20 | +1.50.930 | +3.60.842 |
| Rectangle | -3.20.870 | +5.10.790 | -18.70.332 | -7.70.691 | +2.10.916 | -21.50.410 | -11.50.682 | -1.50.930 | 38.5%13 | +2.10.916 |
| Octagon | -5.30.795 | +3.00.879 | -20.80.302 | -9.80.628 | -0.01.000 | -23.60.377 | -13.60.634 | -3.60.842 | -2.10.916 | 36.4%11 |
Better on the row's stage — deeper at 5 and 10 pointsBetter on the column's stagep < 0.05 on its ownStill there after correcting for how many were tested· fewer than 80 decided matches on one side of the comparison
How significance is decided
- Each gap is two win rates compared with a pooled two-proportion z test, over decided matches only.
- The 95% interval is Newcombe's hybrid score method, which keeps its shape near 0% and 100% where a symmetric interval does not.
- q is p corrected for how many tests were asked at once, by Benjamini–Hochberg at a 5% false discovery rate. A figure is called real on q, never on p alone.
- Standard errors are widened by a measured design effect, because one player appears in many matches and those matches are not independent of each other.
- Stages are assigned at random, so a gap between them is the stage's own effect and not a difference in who chose to play where.