Results with Adversaries

Results using Scenarios

Scenario Difficulty Com­pleted Blight Flipped Average Score Score Model Win Rate Win Model Differ­ential
Dahan Insurrection 4 1 0.0% 65.0 4.428 100.0% 0.143 0.5412
Guard the Isle's Heart 0 1 0.0% 13.0 -8.557 0.0% -0.33 0.0367

Results using Blight Cards

Blight Card Com­pleted Average Score Score Model Win Rate Win Model Differ­ential
A Pall Upon the Land 3 69.67 6.073 100.0% 0.341 2.4144
Aid From Lesser Spirits 1 73.0 5.566 100.0% 0.088 2.0061
All Things Weaken 1 46.0 -0.48 100.0% 0.087 2.2573
Erosion of Will 1 51.0 -1.615 100.0% 0.083 2.2916
Invaders Find the Land to Their Liking 1 40.0 -2.875 100.0% 0.076 0.7619
Memory Fades to Dust 1 32.0 -7.396 0.0% -0.584 1.6343
Promising Farmlands 4 54.75 -1.772 75.0% -0.331 1.8832
Untended Land Crumbles 1 15.0 -5.931 0.0% -0.327 1.7784

Results Using Boards

Board Com­pleted Blight Flipped Average Score Score Model Win Rate Win Model Differ­ential
A 14 64.29% 52.0 0.361 85.71% 0.156 -0.6046
B 19 63.16% 49.58 -2.606 78.95% -0.283 -1.1405
C 18 61.11% 51.39 1.919 83.33% 0.065 -1.0242
D 16 62.5% 48.75 -1.672 81.25% -0.115 -0.9649
E 15 53.33% 52.8 0.749 86.67% 0.35 -0.6148
F 10 50.0% 48.0 -1.534 80.0% -0.033 -0.947
G 9 55.56% 55.0 3.012 77.78% -0.052 -0.9569
H 9 55.56% 48.11 -0.996 77.78% -0.068 -0.9825

Results Using Options

Option Com­pleted Blight Flipped Average Score Score Model Win Rate Win Model Differ­ential
Start of Game Growth 1 100.0% 15.0 -5.931 0.0% -0.327 -0.7975
Using Tokens but Not Events 2 0.0% 35.5 -4.044 100.0% 0.129 0.0767

Terror Level

Terror Level Completed Average Score Win Rate
I 3 22.35 0.0%
II 5 30.84 80.0%
III 7 34.35 100.0%
IV 7 37.52 100.0%

Results

Result Completed
Win: Invaders destroyed (Terror III) 7
Win: Invaders destroyed (Terror II) 3
Win: Terror victory (Terror IV) 7
Lose: Scenario condition 1
Win: Scenario condition 1
Lose: Blight pool ran out 3

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.

Layouts

Layouts for completed games are shown as the same as what they were when the game was started, despite powers like Cast Down Into the Briny Deep.

Data last updated: 2025-04-01 02:56:45 (Pacific Time)