Virtua Fighter 5 REVO · v1.10 · Character Matchup Winrates
Eileen vs Jean
Matches counted562
Win rate55.0%
Widest swing20.0 pts
Survive correction1
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 |
|---|---|---|---|---|---|
| Open | 75.0% | +20.0 | 0.002 | 56 · | |
| Rectangle | 72.5% | +17.5 | 0.021 | 40 · | |
| Low fence | 61.8% | +6.8 | 0.283 | 55 · | |
| Single wall | 56.6% | +1.6 | 0.803 | 53 · | |
| Half fence | 53.4% | -1.6 | 0.774 | 73 · | |
| Breakable full fence | 52.0% | -3.0 | 0.657 | 50 · | |
| Fence and open | 48.7% | -6.3 | 0.415 | 39 · | |
| Octagon | 48.7% | -6.3 | 0.415 | 39 · | |
| Full fence | 45.6% | -9.4 | 0.097 | 68 · | |
| Breakable half fence | 41.9% | -13.0 | 0.029 | 62 · |
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 23.30 on 9 df, p 0.006
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 45.6%68 | -6.40.491 | -7.80.352 | +3.60.675 | -16.20.073 | -11.00.229 | -3.10.755 | -29.4<0.001 | -26.90.007 | -3.10.755 |
| Breakable full fence | +6.40.491 | 52.0%50 | -1.40.876 | +10.10.288 | -9.80.310 | -4.60.639 | +3.30.759 | -23.00.014 | -20.50.047 | +3.30.759 |
| Half fence | +7.80.352 | +1.40.876 | 53.4%73 | +11.50.183 | -8.40.342 | -3.20.723 | +4.70.635 | -21.60.012 | -19.10.048 | +4.70.635 |
| Breakable half fence | -3.60.675 | -10.10.288 | -11.50.183 | 41.9%62 | -19.90.032 | -14.70.117 | -6.80.504 | -33.1<0.001 | -30.60.002 | -6.80.504 |
| Low fence | +16.20.073 | +9.80.310 | +8.40.342 | +19.90.032 | 61.8%55 | +5.20.581 | +13.10.207 | -13.20.135 | -10.70.277 | +13.10.207 |
| Single wall | +11.00.229 | +4.60.639 | +3.20.723 | +14.70.117 | -5.20.581 | 56.6%53 | +7.90.454 | -18.40.043 | -15.90.115 | +7.90.454 |
| Fence and open | +3.10.755 | -3.30.759 | -4.70.635 | +6.80.504 | -13.10.207 | -7.90.454 | 48.7%39 | -26.30.009 | -23.80.030 | +0.01.000 |
| Open | +29.4<0.001 | +23.00.014 | +21.60.012 | +33.1<0.001 | +13.20.135 | +18.40.043 | +26.30.009 | 75.0%56 | +2.50.783 | +26.30.009 |
| Rectangle | +26.90.007 | +20.50.047 | +19.10.048 | +30.60.002 | +10.70.277 | +15.90.115 | +23.80.030 | -2.50.783 | 72.5%40 | +23.80.030 |
| Octagon | +3.10.755 | -3.30.759 | -4.70.635 | +6.80.504 | -13.10.207 | -7.90.454 | -0.01.000 | -26.30.009 | -23.80.030 | 48.7%39 |
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 counted457
Win rate51.0%
Widest swing24.0 pts
Survive correction2
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 |
|---|---|---|---|---|---|
| Open | 75.0% | +24.0 | 0.005 | 32 · | |
| Rectangle | 72.7% | +21.8 | 0.009 | 33 · | |
| Low fence | 58.7% | +7.7 | 0.270 | 46 · | |
| Single wall | 50.0% | -1.0 | 0.888 | 46 · | |
| Octagon | 48.4% | -2.6 | 0.764 | 31 · | |
| Breakable full fence | 46.3% | -4.6 | 0.533 | 41 · | |
| Fence and open | 46.0% | -5.0 | 0.522 | 37 · | |
| Half fence | 45.8% | -5.2 | 0.390 | 59 · | |
| Full fence | 44.8% | -6.2 | 0.315 | 58 · | |
| Breakable half fence | 39.2% | -11.8 | 0.074 | 51 · |
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 19.90 on 9 df, p 0.018
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 44.8%58 | -1.50.882 | -0.90.919 | +5.60.554 | -13.90.160 | -5.20.600 | -1.10.915 | -30.20.006 | -27.90.010 | -3.60.748 |
| Breakable full fence | +1.50.882 | 46.3%41 | +0.60.954 | +7.10.492 | -12.40.249 | -3.70.733 | +0.40.972 | -28.70.014 | -26.40.022 | -2.00.863 |
| Half fence | +0.90.919 | -0.60.954 | 45.8%59 | +6.50.489 | -12.90.188 | -4.20.666 | -0.20.986 | -29.20.007 | -27.00.013 | -2.60.813 |
| Breakable half fence | -5.60.554 | -7.10.492 | -6.50.489 | 39.2%51 | -19.50.055 | -10.80.286 | -6.70.528 | -35.80.001 | -33.50.003 | -9.20.416 |
| Low fence | +13.90.160 | +12.40.249 | +12.90.188 | +19.50.055 | 58.7%46 | +8.70.402 | +12.80.247 | -16.30.137 | -14.00.198 | +10.30.373 |
| Single wall | +5.20.600 | +3.70.733 | +4.20.666 | +10.80.286 | -8.70.402 | 50.0%46 | +4.00.713 | -25.00.026 | -22.70.042 | +1.60.890 |
| Fence and open | +1.10.915 | -0.40.972 | +0.20.986 | +6.70.528 | -12.80.247 | -4.00.713 | 46.0%37 | -29.10.014 | -26.80.023 | -2.40.841 |
| Open | +30.20.006 | +28.70.014 | +29.20.007 | +35.80.001 | +16.30.137 | +25.00.026 | +29.10.014 | 75.0%32 | +2.30.835 | +26.60.030 |
| Rectangle | +27.90.010 | +26.40.022 | +27.00.013 | +33.50.003 | +14.00.198 | +22.70.042 | +26.80.023 | -2.30.835 | 72.7%33 | +24.30.046 |
| Octagon | +3.60.748 | +2.00.863 | +2.60.813 | +9.20.416 | -10.30.373 | -1.60.890 | +2.40.841 | -26.60.030 | -24.30.046 | 48.4%31 |
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 counted105
Win rate72.4%
Widest swing27.6 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 |
|---|---|---|---|---|---|
| Fence and open | 100.0% | +27.6 | 0.378 | 2 · | |
| Single wall | 100.0% | +27.6 | 0.091 | 7 · | |
| Half fence | 85.7% | +13.3 | 0.231 | 14 · | |
| Breakable full fence | 77.8% | +5.4 | 0.705 | 9 · | |
| Low fence | 77.8% | +5.4 | 0.705 | 9 · | |
| Open | 75.0% | +2.6 | 0.744 | 24 · | |
| Rectangle | 71.4% | -0.9 | 0.953 | 7 · | |
| Breakable half fence | 54.5% | -17.8 | 0.162 | 11 · | |
| Full fence | 50.0% | -22.4 | 0.096 | 10 · | |
| Octagon | 50.0% | -22.4 | 0.141 | 8 · |
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 11.26 on 9 df, p 0.258
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 50.0%10 | -27.80.210 | -35.70.058 | -4.50.835 | -27.80.210 | -50.00.026 | -50.00.190 | -25.00.156 | -21.40.377 | +0.01.000 |
| Breakable full fence | +27.80.210 | 77.8%9 | -7.90.624 | +23.20.279 | +0.01.000 | -22.20.182 | -22.20.461 | +2.80.868 | +6.30.771 | +27.80.232 |
| Half fence | +35.70.058 | +7.90.624 | 85.7%14 | +31.20.085 | +7.90.624 | -14.30.293 | -14.30.568 | +10.70.435 | +14.30.432 | +35.70.070 |
| Breakable half fence | +4.50.835 | -23.20.279 | -31.20.085 | 54.5%11 | -23.20.279 | -45.50.036 | -45.50.224 | -20.40.226 | -16.90.474 | +4.50.845 |
| Low fence | +27.80.210 | -0.01.000 | -7.90.624 | +23.20.279 | 77.8%9 | -22.20.182 | -22.20.461 | +2.80.868 | +6.30.771 | +27.80.232 |
| Single wall | +50.00.026 | +22.20.182 | +14.30.293 | +45.50.036 | +22.20.182 | 100.0%7 | +0.01.000 | +25.00.141 | +28.60.127 | +50.00.029 |
| Fence and open | +50.00.190 | +22.20.461 | +14.30.568 | +45.50.224 | +22.20.461 | -0.01.000 | 100.0%2 | +25.00.420 | +28.60.391 | +50.00.197 |
| Open | +25.00.156 | -2.80.868 | -10.70.435 | +20.40.226 | -2.80.868 | -25.00.141 | -25.00.420 | 75.0%24 | +3.60.849 | +25.00.186 |
| Rectangle | +21.40.377 | -6.30.771 | -14.30.432 | +16.90.474 | -6.30.771 | -28.60.127 | -28.60.391 | -3.60.849 | 71.4%7 | +21.40.398 |
| Octagon | -0.01.000 | -27.80.232 | -35.70.070 | -4.50.845 | -27.80.232 | -50.00.029 | -50.00.197 | -25.00.186 | -21.40.398 | 50.0%8 |
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.