Virtua Fighter 5 REVO · v1.10 · Character Matchup Winrates
Eileen vs Kage
Matches counted841
Win rate50.1%
Widest swing-14.3 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 | 56.6% | +6.5 | 0.233 | 76 · | |
| Full fence | 56.5% | +6.4 | 0.296 | 62 · | |
| Low fence | 54.7% | +4.6 | 0.441 | 64 · | |
| Rectangle | 52.3% | +2.2 | 0.617 | 109 | |
| Breakable half fence | 50.5% | +0.5 | 0.922 | 93 | |
| Single wall | 48.9% | -1.1 | 0.817 | 94 | |
| Open | 48.5% | -1.6 | 0.790 | 66 · | |
| Half fence | 44.4% | -5.6 | 0.211 | 108 | |
| Octagon | 42.5% | -7.6 | 0.175 | 73 · | |
| Fence and open | 35.7% | -14.3 | 0.056 | 42 · |
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 9.57 on 9 df, p 0.386
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 56.5%62 | -0.10.988 | +12.00.132 | +5.90.470 | +1.80.842 | +7.50.358 | +20.70.038 | +8.00.367 | +4.20.600 | +14.00.105 |
| Breakable full fence | +0.10.988 | 56.6%76 | +12.10.105 | +6.00.434 | +1.90.822 | +7.60.321 | +20.90.030 | +8.10.335 | +4.30.565 | +14.10.085 |
| Half fence | -12.00.132 | -12.10.105 | 44.4%108 | -6.10.388 | -10.20.194 | -4.50.523 | +8.70.331 | -4.00.604 | -7.80.247 | +2.00.792 |
| Breakable half fence | -5.90.470 | -6.00.434 | +6.10.388 | 50.5%93 | -4.20.609 | +1.60.827 | +14.80.110 | +2.10.799 | -1.80.803 | +8.10.301 |
| Low fence | -1.80.842 | -1.90.822 | +10.20.194 | +4.20.609 | 54.7%64 | +5.80.478 | +19.00.056 | +6.20.479 | +2.40.761 | +12.20.153 |
| Single wall | -7.50.358 | -7.60.321 | +4.50.523 | -1.60.827 | -5.80.478 | 48.9%94 | +13.20.152 | +0.50.955 | -3.40.633 | +6.50.405 |
| Fence and open | -20.70.038 | -20.90.030 | -8.70.331 | -14.80.110 | -19.00.056 | -13.20.152 | 35.7%42 | -12.80.192 | -16.60.068 | -6.80.477 |
| Open | -8.00.367 | -8.10.335 | +4.00.604 | -2.10.799 | -6.20.479 | -0.50.955 | +12.80.192 | 48.5%66 | -3.80.625 | +6.00.477 |
| Rectangle | -4.20.600 | -4.30.565 | +7.80.247 | +1.80.803 | -2.40.761 | +3.40.633 | +16.60.068 | +3.80.625 | 52.3%109 | +9.80.193 |
| Octagon | -14.00.105 | -14.10.085 | -2.00.792 | -8.10.301 | -12.20.153 | -6.50.405 | +6.80.477 | -6.00.477 | -9.80.193 | 42.5%73 |
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 counted566
Win rate48.2%
Widest swing-17.2 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 | 56.6% | +8.4 | 0.200 | 53 · | |
| Low fence | 56.5% | +8.3 | 0.241 | 46 · | |
| Full fence | 53.3% | +5.1 | 0.475 | 45 · | |
| Open | 51.3% | +3.0 | 0.693 | 39 · | |
| Rectangle | 50.0% | +1.8 | 0.748 | 72 · | |
| Single wall | 46.1% | -2.1 | 0.753 | 52 · | |
| Breakable half fence | 45.3% | -2.9 | 0.620 | 64 · | |
| Half fence | 43.2% | -5.0 | 0.357 | 74 · | |
| Octagon | 42.9% | -5.4 | 0.396 | 56 · | |
| Fence and open | 31.0% | -17.2 | 0.057 | 29 · |
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 8.57 on 9 df, p 0.478
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 53.3%45 | -3.30.746 | +10.10.285 | +8.00.409 | -3.20.760 | +7.20.481 | +22.30.060 | +2.00.851 | +3.30.726 | +10.50.295 |
| Breakable full fence | +3.30.746 | 56.6%53 | +13.40.137 | +11.30.224 | +0.10.993 | +10.40.284 | +25.60.027 | +5.30.613 | +6.60.465 | +13.70.151 |
| Half fence | -10.10.285 | -13.40.137 | 43.2%74 | -2.10.807 | -13.30.157 | -2.90.746 | +12.20.255 | -8.00.415 | -6.80.413 | +0.40.965 |
| Breakable half fence | -8.00.409 | -11.30.224 | +2.10.807 | 45.3%64 | -11.20.246 | -0.80.928 | +14.30.194 | -6.00.556 | -4.70.585 | +2.50.787 |
| Low fence | +3.20.760 | -0.10.993 | +13.30.157 | +11.20.246 | 56.5%46 | +10.40.306 | +25.50.031 | +5.20.629 | +6.50.489 | +13.70.170 |
| Single wall | -7.20.481 | -10.40.284 | +2.90.746 | +0.80.928 | -10.40.306 | 46.1%52 | +15.10.184 | -5.10.628 | -3.90.672 | +3.30.730 |
| Fence and open | -22.30.060 | -25.60.027 | -12.20.255 | -14.30.194 | -25.50.031 | -15.10.184 | 31.0%29 | -20.20.095 | -19.00.083 | -11.80.289 |
| Open | -2.00.851 | -5.30.613 | +8.00.415 | +6.00.556 | -5.20.629 | +5.10.628 | +20.20.095 | 51.3%39 | +1.30.897 | +8.40.418 |
| Rectangle | -3.30.726 | -6.60.465 | +6.80.413 | +4.70.585 | -6.50.489 | +3.90.672 | +19.00.083 | -1.30.897 | 50.0%72 | +7.10.422 |
| Octagon | -10.50.295 | -13.70.151 | -0.40.965 | -2.50.787 | -13.70.170 | -3.30.730 | +11.80.289 | -8.40.418 | -7.10.422 | 42.9%56 |
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 counted275
Win rate53.8%
Widest swing-12.6 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 |
|---|---|---|---|---|---|
| Full fence | 64.7% | +10.9 | 0.353 | 17 · | |
| Breakable half fence | 62.1% | +8.2 | 0.346 | 29 · | |
| Rectangle | 56.8% | +2.9 | 0.700 | 37 · | |
| Breakable full fence | 56.5% | +2.7 | 0.786 | 23 · | |
| Single wall | 52.4% | -1.4 | 0.839 | 42 · | |
| Low fence | 50.0% | -3.8 | 0.737 | 18 · | |
| Half fence | 47.1% | -6.8 | 0.398 | 34 · | |
| Fence and open | 46.1% | -7.7 | 0.570 | 13 · | |
| Open | 44.4% | -9.4 | 0.304 | 27 · | |
| Octagon | 41.2% | -12.6 | 0.280 | 17 · |
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 4.73 on 9 df, p 0.857
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 64.7%17 | +8.20.601 | +17.60.234 | +2.60.858 | +14.70.380 | +12.30.388 | +18.60.310 | +20.30.190 | +8.00.581 | +23.50.169 |
| Breakable full fence | -8.20.601 | 56.5%23 | +9.50.483 | -5.50.686 | +6.50.678 | +4.10.749 | +10.40.549 | +12.10.395 | -0.20.986 | +15.30.337 |
| Half fence | -17.60.234 | -9.50.483 | 47.1%34 | -15.00.233 | -2.90.840 | -5.30.645 | +0.90.956 | +2.60.839 | -9.70.414 | +5.90.691 |
| Breakable half fence | -2.60.858 | +5.50.686 | +15.00.233 | 62.1%29 | +12.10.416 | +9.70.418 | +15.90.335 | +17.60.186 | +5.30.663 | +20.90.170 |
| Low fence | -14.70.380 | -6.50.678 | +2.90.840 | -12.10.416 | 50.0%18 | -2.40.866 | +3.90.833 | +5.60.714 | -6.80.637 | +8.80.600 |
| Single wall | -12.30.388 | -4.10.749 | +5.30.645 | -9.70.418 | +2.40.866 | 52.4%42 | +6.20.695 | +7.90.520 | -4.40.697 | +11.20.436 |
| Fence and open | -18.60.310 | -10.40.549 | -0.90.956 | -15.90.335 | -3.90.833 | -6.20.695 | 46.1%13 | +1.70.919 | -10.60.509 | +5.00.785 |
| Open | -20.30.190 | -12.10.395 | -2.60.839 | -17.60.186 | -5.60.714 | -7.90.520 | -1.70.919 | 44.4%27 | -12.30.330 | +3.30.831 |
| Rectangle | -8.00.581 | +0.20.986 | +9.70.414 | -5.30.663 | +6.80.637 | +4.40.697 | +10.60.509 | +12.30.330 | 56.8%37 | +15.60.287 |
| Octagon | -23.50.169 | -15.30.337 | -5.90.691 | -20.90.170 | -8.80.600 | -11.20.436 | -5.00.785 | -3.30.831 | -15.60.287 | 41.2%17 |
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.