Results with Adversaries

Results using Scenarios

Scenario Difficulty Com­pleted Blight Flipped Average Score Win Rate Win Model Differ­ential Model (Diff≥10)
A Diversity of Spirits 0 2 0.0% 18.0 50.0%
Blitz 0 28 35.71% 24.18 32.14% -0.931
Dahan Insurrection 4 29 24.14% 46.86 62.07% -0.188 -0.4363 0.046
Despicable Theft 2 1 0.0% 31.0 100.0%
Elemental Invocation 1 5 40.0% 38.8 40.0% -0.835
Guard the Isle's Heart 0 157 5.1% 33.4 59.87% -0.232 -0.7843 -0.145
Powers Long Forgotten 1 2 50.0% 37.5 50.0% 0.368 0.9913
Rituals of Terror 3 8 50.0% 9.88 0.0% -1.255
Rituals of the Destroying Flame 3 2 0.0% 28.5 50.0%
Second Wave 0 58 44.83% 25.72 74.14% 0.02 0.1373 0.097
Varied Terrains 2 5 40.0% 16.0 60.0%
Ward the Shores 2 10 10.0% 14.8 30.0% -0.334

Results using Blight Cards

Blight Card Com­pleted Average Score Win Rate Win Model Differ­ential Model (Diff≥10)
A Pall Upon the Land 21 41.9 61.9% 0.201 0.4507 0.275
Aid From Lesser Spirits 20 32.2 55.0% -0.296 -0.4143 0.228
All Things Weaken 26 37.96 84.62% 0.153 0.4901 1.225
Attenuated Essence 8 29.13 50.0% 0.212 0.2389 -0.015
Back Against the Wall 17 47.0 94.12% 0.36 0.3606 1.175
Blight Corrodes the Spirit 6 24.0 50.0% -0.363 -0.1456 -0.324
Burn Brightest Before the End 7 33.43 71.43% 0.228 0.2092 0.496
Disintegrating Ecosystem 8 24.25 50.0% -0.294 0.0988 0.301
Downward Spiral 12 22.75 58.33% -0.117
Erosion of Will 19 30.32 47.37% -0.364 -0.0119 -0.807
Intensifying Exploitation 9 23.11 77.78%
Invaders Find the Land to Their Liking 11 45.09 90.91% 0.353 -0.1711 0.358
Memory Fades to Dust 17 34.94 58.82% -0.252
Power Corrodes the Spirit 20 34.7 50.0% 0.375 0.5969 0.19
Promising Farmlands 13 33.85 46.15% -0.423 -0.1405 -0.124
Shattered Fragments of Power 12 39.0 83.33% -0.142
Slow Dissolution of Will 3 41.67 66.67% 0.144 0.5408 0.2
Strong Earth Shatters Slowly 9 36.89 77.78% -0.194
The Border of Life and Death 1 58.0 100.0%
Thriving Communities 17 29.18 47.06% -0.855 -0.4988 0.055
Thriving Crops 4 27.5 25.0% 0.304
Unnatural Proliferation 19 35.42 47.37% 0.544 0.7059 0.462
Untended Land Crumbles 14 32.64 64.29% 0.571

Results Using Boards

Board Com­pleted Blight Flipped Average Score Win Rate Win Model Differ­ential Model (Diff≥10)
A 892 25.93% 29.4 66.93% 0.053 1.0574 0.358
B 908 26.02% 28.74 64.1% -0.42 0.4995 -0.265
C 946 25.61% 28.45 65.22% 1.039 1.7731 -0.271
D 944 25.66% 27.95 65.47% -0.193 0.7845 -0.002
E 974 24.97% 28.41 65.5% 0.176 0.9954 0.188
F 913 26.32% 28.07 63.96% -0.726 0.1474 0.068
G 616 25.49% 27.06 63.47% -0.055 0.7547 -0.539
H 612 25.0% 26.89 66.99% 0.19 1.0051 0.4

Results Using Options

Option Com­pleted Blight Flipped Average Score Win Rate Win Model Differ­ential Model (Diff≥10)
No Blight Card 1 0.0% 21.0 100.0%
Not Using Events or Tokens 1 100.0% 16.0 100.0%
Skip Initial Invader Actions 41 7.5% 29.51 48.78% -0.147 -0.7313 -1.064
Start of Game Growth 129 26.56% 32.71 52.71% 0.17 -0.3435 0.248
Unlimited Undo 78 10.26% 35.19 56.41% 0.726 0.6169 0.727
Using Tokens but Not Events 98 10.31% 24.81 70.41% -0.115 -0.1408 -0.035

Terror Level

Terror Level Completed Average Score Win Rate
I 295 13.33 1.36%
II 361 30.1 78.67%
III 384 34.83 93.75%
IV 102 38.67 97.06%

Results

Result Completed
Win: Invaders destroyed (Terror I) 4
Win: Invaders destroyed (Terror III) 349
Win: Invaders destroyed (Terror II) 274
Win: Terror victory (Terror IV) 99
Game abandoned (v.3.0+) 243
Lose: Invader deck ran out 2
Lose: Adversary condition 69
Lose: Scenario condition 35
Win: Scenario condition 21
Lose: Blight pool ran out 38
Lose: Spirit destroyed 8

Notes

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.

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. model.

Differential

The difference between the logistic regression coefficient for this item using this Spirit, as compared to using this item in general. A negative number means that this Spirit underperforms using this item, and a positive number means that it overperforms.

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.

Data last updated: 2026-08-07 03:46:17 (Pacific Time)