Results vs. Adversaries

Adversary Completed Completion Rate Average Score Score Model Win Rate Deviation p(χ²) Win Model Differential
The Kingdom of Brandenburg-Prussia 6903 54.76% 32.49 4.882 66.8% -0.016 0.0052 -0.438 -0.0044
The Kingdom of England 5112 54.18% 31.38 3.24 52.66% -0.095 0.0 -1.338 -0.0196
The Kingdom of France (Plantation Colony) 3978 63.12% 31.78 3.227 35.39% -0.222 0.0 -2.294 -0.5133
The Kingdom of Sweden 4001 55.76% 30.64 3.167 66.61% -0.017 0.0239 -0.396 0.1082

Results in Scenarios

Scenario Difficulty Completed Completion Rate Average Score Score Model Win Rate Deviation p(χ²) Win Model Differential
Blitz 0 613 54.06% 22.34 -2.212 69.0% 0.021 0.2786 -0.22 0.2435
Dahan Insurrection 4 588 57.87% 44.56 8.125 63.61% -0.034 0.078 -0.488 -0.1394
Guard the Isle's Heart 0 2079 62.36% 39.86 5.172 67.05% -0.018 0.074 -0.44 -0.1339
Powers Long Forgotten 1 265 48.8% 36.53 2.214 69.06% 0.009 0.7588 0.302 0.6039
Rituals of Terror 3 248 54.27% 36.5 4.35 60.89% -0.03 0.3188 -0.014 0.6557
Rituals of the Destroying Flame 3 163 39.95% 31.43 2.045 58.9% -0.011 0.7792 -0.117 0.5895
Second Wave 0 2092 56.24% 26.85 0.472 70.98% 0.029 0.004 -0.174 0.2807
Ward the Shores 2 252 51.32% 32.23 1.822 54.76% -0.071 0.0197 -0.407 0.5652

Results using Layouts

Results using Blight Cards

Blight Card Completed Average Score Score Model Win Rate Deviation p(χ²) Win Model Differential
A Pall Upon the Land 1083 26.09 -1.239 39.8% -0.17 0.0 -1.992 0.1377
Aid From Lesser Spirits 902 26.58 -0.938 48.78% -0.104 0.0 -1.686 0.3069
Back Against the Wall 963 27.9 -0.307 44.65% -0.123 0.0 -1.836 0.3073
Disintegrating Ecosystem 952 22.28 -2.823 34.66% -0.196 0.0 -2.187 0.1062
Downward Spiral 3376 19.38 -2.983 41.0% -0.193 0.0 -2.009 0.0501
Erosion of Will 1030 23.07 -2.398 37.28% -0.174 0.0 -2.13 0.1553
Memory Fades to Dust 3297 19.54 -2.999 38.67% -0.187 0.0 -2.132 0.127
Promising Farmlands 1010 23.72 -2.22 36.73% -0.177 0.0 -2.131 0.1569
Tipping Point 968 24.36 -1.863 42.36% -0.126 0.0 -1.823 0.4053

Results Starting on Boards

Board Completed Completion Rate Average Score Score Model Win Rate Deviation p(χ²) Win Model Differential
A 8921 48.67% 22.56 -0.753 63.41% -0.049 0.0 -0.129 -0.0559
B 9544 51.91% 24.21 -0.021 68.69% 0.003 0.5789 0.058 0.0315
C 10722 53.16% 24.66 0.138 69.0% -0.001 0.8354 0.046 -0.1918
D 9870 52.94% 24.45 0.077 67.67% -0.008 0.088 0.17 0.1539
East 696 51.06% 34.93 1.183 54.74% -0.115 0.0 -0.064 -0.1062
Northeast 731 48.83% 35.16 0.556 64.02% -0.025 0.1463 -0.148 -0.1462
Northwest 657 51.49% 34.45 0.181 58.9% -0.079 0.0 -0.247 -0.276
West 670 39.39% 42.92 3.693 62.84% -0.024 0.1915 0.336 0.5958

Results Using Boards

Board Completed Completion Rate Average Score Score Model Win Rate Deviation p(χ²) Win Model Differential
A 16167 49.13% 25.48 0.02 69.47% 0.012 0.0013 0.117 0.1898
B 16569 50.67% 26.2 0.407 71.87% 0.034 0.0 0.118 0.0917
C 17478 51.71% 26.26 0.506 71.56% 0.025 0.0 0.094 -0.1441
D 16711 51.18% 26.05 0.207 70.58% 0.021 0.0 -0.073 -0.0886
East 1684 45.7% 40.29 1.937 63.12% -0.031 0.0068 -0.083 -0.1252
Northeast 1585 45.66% 40.9 2.271 67.57% 0.01 0.3921 0.148 0.1496
Northwest 1504 44.82% 40.69 1.826 66.16% -0.007 0.5835 0.118 0.0884
West 1598 44.35% 39.96 1.059 63.2% -0.02 0.0876 -0.283 -0.0232

Results Using Options

Option Completed Completion Rate Average Score Score Model Win Rate Deviation p(χ²) Win Model Differential
No Blight Card 5196 38.33% 16.28 -2.329 62.43% -0.048 0.0 -0.642 0.4267
Not Using Events or Tokens 16769 44.3% 20.15 -1.782 68.5% 0.002 0.5562 -0.167 0.0507
Skip Initial Invader Actions 1828 62.2% 31.09 2.451 90.37% 0.061 0.0 1.011 0.1644
Start of Game Growth 2144 57.74% 30.9 2.17 86.19% 0.034 0.0 0.301 0.0159
Unlimited Undo 4402 51.5% 28.26 1.463 78.08% 0.009 0.1478 0.273 -0.1677
Using Tokens but Not Events 4319 58.2% 24.1 -0.777 72.91% -0.022 0.0007 -0.144 -0.1877

Results With Allies

Terror Level

Terror Level Completed Average Score Win Rate
I 7396 22.24 23.76%
II 15049 29.69 66.66%
III 13970 32.43 77.37%
IV 5396 36.13 99.13%

Power Progression

Score Model: -2.909 Win Model: -0.55
Power Progression? Completed Completion Rate Average Score Win Rate
Standard 36681 54.46% 26.25 67.94%
Power Progression 5130 36.62% 14.97 58.97%

Results

Result Completed
Win: Scenario condition 512
Lose: Scenario condition 491
Lose: Adversary condition 3145
Win: Invaders destroyed 22043
Lose: Invader deck ran out 3355
Win: Terror victory 5299
Win: Sacrifice victory 93
Lose: Spirit destroyed 199
Lose: Blight pool ran out 6674

Number of Players

Score Model: 0.537 Win Model: 0.155
Num. Completed Completion Rate Average Score Win Rate Dev. p(χ²)
1 22947 53.44% 21.73 61.64% -0.066 0.0
2 10536 49.3% 25.55 69.8% 0.014 0.0029
3 4035 52.33% 31.12 76.03% 0.021 0.0023
4 4293 45.97% 34.03 78.76% 0.043 0.0

Online Multiplayer

Score Model: -1.333 Win Model: -0.082
Multiplayer? Completed Completion Rate Average Score Win Rate
Single-Player 39498 50.49% 24.92 66.51%
Multiplayer 2313 73.76% 23.88 72.42%

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. Exception: For Difficulty, the Score Model is a separate model, using only difficulty as a predictor.

Deviation

The difference between the actual win rate of this combination of elements and the win rates of each of those elements on their own, averaged. A positive value means that this combination results in a win more often than would be expected.

p(χ²)

This is the significance value of a χ² test comparing the observed data and expected value. In most cases, this expected value is the mean of the win rates of each element. For team position, the expected value is an equal likelihood of winning in all positions. Lower p-values (no greater than 0.01) mean a greater likelihood that the difference is meaningful and not due to chance.

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.
Exception: For Difficulty, the Win Model is a separate model, using only difficulty as a predictor.

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

Diagrams of the layouts are on the main page. 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.

Last updated: Sep 08, 2023, 09:55 AM PDT