Virtua Fighter 5 REVO · v1.10 · Character Matchup Winrates
Eileen vs Lau
Matches counted939
Win rate51.5%
Widest swing10.6 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 |
|---|---|---|---|---|---|
| Breakable half fence | 62.1% | +10.6 | 0.023 | 103 | |
| Breakable full fence | 61.6% | +10.1 | 0.034 | 99 | |
| Open | 54.3% | +2.7 | 0.579 | 94 | |
| Full fence | 51.4% | -0.2 | 0.970 | 109 | |
| Low fence | 51.1% | -0.4 | 0.936 | 88 | |
| Fence and open | 50.0% | -1.5 | 0.838 | 42 · | |
| Rectangle | 47.2% | -4.3 | 0.339 | 108 | |
| Single wall | 46.0% | -5.6 | 0.275 | 87 | |
| Half fence | 43.8% | -7.7 | 0.170 | 73 · | |
| Octagon | 43.8% | -7.7 | 0.125 | 89 |
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 14.72 on 9 df, p 0.099
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 51.4%109 | -10.20.137 | +7.50.318 | -10.80.114 | +0.20.973 | +5.40.452 | +1.40.880 | -2.90.682 | +4.20.541 | +7.60.290 |
| Breakable full fence | +10.20.137 | 61.6%99 | +17.80.021 | -0.50.939 | +10.50.149 | +15.60.033 | +11.60.201 | +7.40.300 | +14.40.038 | +17.80.015 |
| Half fence | -7.50.318 | -17.80.021 | 43.8%73 | -18.30.016 | -7.30.356 | -2.10.786 | -6.20.523 | -10.40.182 | -3.40.654 | +0.00.998 |
| Breakable half fence | +10.80.114 | +0.50.939 | +18.30.016 | 62.1%103 | +11.00.126 | +16.20.026 | +12.10.178 | +7.90.262 | +14.90.030 | +18.30.011 |
| Low fence | -0.20.973 | -10.50.149 | +7.30.356 | -11.00.126 | 51.1%88 | +5.20.495 | +1.10.904 | -3.10.674 | +3.90.586 | +7.30.330 |
| Single wall | -5.40.452 | -15.60.033 | +2.10.786 | -16.20.026 | -5.20.495 | 46.0%87 | -4.00.668 | -8.30.266 | -1.20.862 | +2.20.774 |
| Fence and open | -1.40.880 | -11.60.201 | +6.20.523 | -12.10.178 | -1.10.904 | +4.00.668 | 50.0%42 | -4.30.646 | +2.80.760 | +6.20.508 |
| Open | +2.90.682 | -7.40.300 | +10.40.182 | -7.90.262 | +3.10.674 | +8.30.266 | +4.30.646 | 54.3%94 | +7.00.319 | +10.40.158 |
| Rectangle | -4.20.541 | -14.40.038 | +3.40.654 | -14.90.030 | -3.90.586 | +1.20.862 | -2.80.760 | -7.00.319 | 47.2%108 | +3.40.633 |
| Octagon | -7.60.290 | -17.80.015 | -0.00.998 | -18.30.011 | -7.30.330 | -2.20.774 | -6.20.508 | -10.40.158 | -3.40.633 | 43.8%89 |
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 counted582
Win rate51.7%
Widest swing-10.5 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 |
|---|---|---|---|---|---|
| Breakable half fence | 60.9% | +9.2 | 0.105 | 69 · | |
| Breakable full fence | 55.3% | +3.6 | 0.606 | 47 · | |
| Open | 55.1% | +3.4 | 0.553 | 69 · | |
| Low fence | 54.1% | +2.4 | 0.694 | 61 · | |
| Half fence | 53.1% | +1.3 | 0.844 | 49 · | |
| Fence and open | 51.9% | +0.1 | 0.989 | 27 · | |
| Full fence | 50.0% | -1.7 | 0.783 | 58 · | |
| Octagon | 48.9% | -2.8 | 0.691 | 47 · | |
| Single wall | 47.2% | -4.5 | 0.487 | 53 · | |
| Rectangle | 41.2% | -10.5 | 0.064 | 68 · |
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 6.72 on 9 df, p 0.666
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 50.0%58 | -5.30.587 | -3.10.752 | -10.90.219 | -4.10.655 | +2.80.766 | -1.90.874 | -5.10.568 | +8.80.321 | +1.10.914 |
| Breakable full fence | +5.30.587 | 55.3%47 | +2.30.824 | -5.50.551 | +1.20.899 | +8.20.416 | +3.50.773 | +0.20.979 | +14.10.135 | +6.40.536 |
| Half fence | +3.10.752 | -2.30.824 | 53.1%49 | -7.80.398 | -1.00.914 | +5.90.552 | +1.20.920 | -2.00.829 | +11.90.203 | +4.10.686 |
| Breakable half fence | +10.90.219 | +5.50.551 | +7.80.398 | 60.9%69 | +6.80.435 | +13.70.132 | +9.00.420 | +5.80.490 | +19.70.021 | +11.90.204 |
| Low fence | +4.10.655 | -1.20.899 | +1.00.914 | -6.80.435 | 54.1%61 | +6.90.460 | +2.20.846 | -1.00.911 | +12.90.142 | +5.20.595 |
| Single wall | -2.80.766 | -8.20.416 | -5.90.552 | -13.70.132 | -6.90.460 | 47.2%53 | -4.70.692 | -7.90.387 | +6.00.510 | -1.80.860 |
| Fence and open | +1.90.874 | -3.50.773 | -1.20.920 | -9.00.420 | -2.20.846 | +4.70.692 | 51.9%27 | -3.20.776 | +10.70.345 | +2.90.809 |
| Open | +5.10.568 | -0.20.979 | +2.00.829 | -5.80.490 | +1.00.911 | +7.90.387 | +3.20.776 | 55.1%69 | +13.90.104 | +6.10.516 |
| Rectangle | -8.80.321 | -14.10.135 | -11.90.203 | -19.70.021 | -12.90.142 | -6.00.510 | -10.70.345 | -13.90.104 | 41.2%68 | -7.80.410 |
| Octagon | -1.10.914 | -6.40.536 | -4.10.686 | -11.90.204 | -5.20.595 | +1.80.860 | -2.90.809 | -6.10.516 | +7.80.410 | 48.9%47 |
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 counted357
Win rate51.3%
Widest swing-26.3 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 |
|---|---|---|---|---|---|
| Breakable full fence | 67.3% | +16.1 | 0.012 | 52 · | |
| Breakable half fence | 64.7% | +13.4 | 0.099 | 34 · | |
| Rectangle | 57.5% | +6.2 | 0.402 | 40 · | |
| Full fence | 52.9% | +1.7 | 0.795 | 51 · | |
| Open | 52.0% | +0.7 | 0.939 | 25 · | |
| Fence and open | 46.7% | -4.6 | 0.716 | 15 · | |
| Low fence | 44.4% | -6.8 | 0.461 | 27 · | |
| Single wall | 44.1% | -7.1 | 0.381 | 34 · | |
| Octagon | 38.1% | -13.2 | 0.069 | 42 · | |
| Half fence | 25.0% | -26.3 | 0.008 | 24 · |
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 19.36 on 9 df, p 0.022
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 52.9%51 | -14.40.136 | +27.90.023 | -11.80.282 | +8.50.475 | +8.80.425 | +6.30.669 | +0.90.938 | -4.60.664 | +14.80.153 |
| Breakable full fence | +14.40.136 | 67.3%52 | +42.3<0.001 | +2.60.803 | +22.90.050 | +23.20.033 | +20.60.145 | +15.30.194 | +9.80.334 | +29.20.005 |
| Half fence | -27.90.023 | -42.3<0.001 | 25.0%24 | -39.70.003 | -19.40.147 | -19.10.136 | -21.70.163 | -27.00.052 | -32.50.011 | -13.10.278 |
| Breakable half fence | +11.80.282 | -2.60.803 | +39.70.003 | 64.7%34 | +20.30.114 | +20.60.088 | +18.00.236 | +12.70.326 | +7.20.527 | +26.60.021 |
| Low fence | -8.50.475 | -22.90.050 | +19.40.147 | -20.30.114 | 44.4%27 | +0.30.980 | -2.20.890 | -7.60.586 | -13.10.294 | +6.30.600 |
| Single wall | -8.80.425 | -23.20.033 | +19.10.136 | -20.60.088 | -0.30.980 | 44.1%34 | -2.50.869 | -7.90.549 | -13.40.251 | +6.00.595 |
| Fence and open | -6.30.669 | -20.60.145 | +21.70.163 | -18.00.236 | +2.20.890 | +2.50.869 | 46.7%15 | -5.30.744 | -10.80.472 | +8.60.561 |
| Open | -0.90.938 | -15.30.194 | +27.00.052 | -12.70.326 | +7.60.586 | +7.90.549 | +5.30.744 | 52.0%25 | -5.50.664 | +13.90.267 |
| Rectangle | +4.60.664 | -9.80.334 | +32.50.011 | -7.20.527 | +13.10.294 | +13.40.251 | +10.80.472 | +5.50.664 | 57.5%40 | +19.40.079 |
| Octagon | -14.80.153 | -29.20.005 | +13.10.278 | -26.60.021 | -6.30.600 | -6.00.595 | -8.60.561 | -13.90.267 | -19.40.079 | 38.1%42 |
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.