Spirits

Adversaries

Scenarios

Layouts

Boards

Board Com­pleted Blight Flip Rate Average Score Score Model Win Rate Win Model Model (Diff≥10)
A 657112 45.42% 30.19 -0.72 72.72% -0.886 -0.817
B 674457 44.69% 31.3 -0.171 73.85% -0.777 -0.681
C 774225 44.38% 31.47 0.349 75.62% -0.629 -0.623
D 626051 44.7% 30.58 -0.646 73.92% -0.83 -0.777
E 259761 45.73% 35.17 0.625 74.07% -0.644 -0.611
F 325327 44.06% 33.81 0.229 75.21% -0.738 -0.716
G 292468 44.56% 33.23 0.027 74.82% -0.767 -0.695
H 301451 42.9% 34.01 0.556 76.07% -0.686 -0.61
East 102099 45.09% 40.59 1.503 66.27% -0.716 -0.835
Northeast 59644 43.19% 41.59 0.767 67.27% -0.894 -0.941
Northwest 45790 42.01% 41.25 0.891 68.6% -0.625 -0.883
Southeast 16149 41.5% 37.62 -0.37 70.54% -0.682 -1.242
Southwest 14870 44.57% 34.03 -2.674 66.01% -1.284 -1.407
West 86243 45.58% 39.05 0.596 65.41% -1.023 -0.896

Options

Option Com­pleted Blight Flip Rate Average Score Score Model Win Rate Win Model Model (Diff≥10)
No Blight Card 234782 0.0% 19.01 -4.337 69.32% -0.826 -0.652
Not Using Events or Tokens 638906 45.21% 23.16 -3.159 72.82% -0.316 -0.321
Skip Initial Invader Actions 88760 14.27% 39.36 3.426 90.15% 0.555 0.213
Start of Game Growth 127755 17.2% 38.94 3.526 88.65% 0.431 0.574
Unlimited Undo 301099 37.09% 34.79 0.717 81.5% 0.117 0.774
Using Tokens but Not Events 305689 32.77% 30.18 -0.894 81.52% 0.08 -0.014

Blight Cards

Blight Card Com­pleted Average Score Score Model Win Rate Win Model Model (Diff≥10)

Minor Power Cards

Major Power Cards

Difficulty

Number of Players

Score Model: 0.09 Win Model: 0.66
Number Completed Average Score Win Rate
1 2292440 31.09 71.83%
2 516906 32.07 74.63%
3 137888 34.43 78.27%
4 91089 38.62 80.4%
5 1596 34.42 82.27%
6 5788 37.53 79.37%

Wave (in Second Wave Scenario)

Score Model: -0.09 Win Model: 0.04

Notes

Win Model

Logistic regression coefficient using all independent variables as predictors, and whether the game was won or not as the outcome. Higher values indicate greater likelihood of winning when present in the game. For continuous variables (e.g. number of players), this number is per unit. Only games completed within the last 30 days are included in the model. All models omit the user with ID starting with 83fcac33, for extreme outlying behavior.

Score Model

Ridge regression coefficient using all independent variables as predictors, and the score as the outcome. This corresponds 1:1 with score, e.g. a coefficient of +1 means a predicted score 1 higher than average. Ridge regression is used instead of standard linear regression because of high multicollinearity. Only games completed within the last 30 days are included in the model.

Model (Diff ≥10)

Same as Win Model, but instead counts all games of difficulty 10 or higher, for all time.

Layouts

Diagrams of the layouts are on the main page. Data collected before v.2.7.1 (May 2, 2025) use the end game state, even if the island layout changed due to powers like Cast Down Into the Briny Deep. Data collected from v.2.7.1 onward uses the layout as it was at setup.

Difficulty

Difficulty is calculated treating England 6 as difficulty 11, "Start of Game Growth" as -1, and "Skip Initial Invader Actions" as -2. Use of the Thematic island is +1 difficulty if tokens are used, +3 if they are not used. Scenarios with variable difficulty use the average or "assumed" value.

Difficulty Model

Logistic regression coefficient, only looking at games involving this Spirit, using difficulty to predict win likelihood. The lower the value, the worse this Spirit is affected by high difficulty.

Power Cards

Power card stats include the average difficulty level, average score, and win percentage when the card is owned by the player at the end of the game. "Discarded" is how often the card is in the discard pile, which could be by having not been chosen or by being forgotten, and not shuffled back in.

Data last updated: 2025-11-21 03:39:51 (Pacific Time)