Results vs. Adversaries

Adversary Completed Completion Rate Average Score Score Model Win Rate Deviation p(χ²) Win Model Differential
The Kingdom of Brandenburg-Prussia 5968 60.25% 39.84 5.216 77.41% 0.048 0.0 -0.381 0.053
The Kingdom of England 6989 61.49% 42.72 6.197 66.63% 0.038 0.0 -1.131 0.1868
The Kingdom of France (Plantation Colony) 5026 64.94% 37.97 3.295 49.06% -0.09 0.0 -1.992 -0.2112
The Kingdom of Sweden 4472 60.29% 37.23 3.384 74.26% 0.021 0.0017 -0.552 -0.0472

Results in Scenarios

Scenario Difficulty Completed Completion Rate Average Score Score Model Win Rate Deviation p(χ²) Win Model Differential
Blitz 0 259 55.22% 31.37 -1.401 67.18% -0.013 0.6518 -0.36 0.1035
Dahan Insurrection 4 394 57.52% 50.28 7.0 53.55% -0.15 0.0 -1.067 -0.7186
Guard the Isle's Heart 0 3197 64.13% 44.89 4.713 63.9% -0.099 0.0 -0.896 -0.5897
Powers Long Forgotten 1 218 50.46% 37.15 -0.165 71.1% 0.0 0.9916 -0.019 0.2832
Rituals of Terror 3 222 54.81% 36.94 1.792 61.71% -0.031 0.3402 -0.437 0.2332
Rituals of the Destroying Flame 3 149 42.45% 35.21 0.929 59.06% -0.015 0.7165 -0.463 0.2434
Second Wave 0 1683 58.48% 30.11 -1.411 74.27% 0.037 0.0009 -0.376 0.0784
Ward the Shores 2 239 54.44% 31.94 -1.739 55.65% -0.069 0.0274 -1.156 -0.1831

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 1219 31.82 -1.959 54.22% -0.03 0.0353 -1.751 0.3785
Aid From Lesser Spirits 1102 34.81 -0.501 59.53% -0.002 0.9155 -1.481 0.5111
Back Against the Wall 1140 33.56 -1.207 53.95% -0.034 0.0206 -1.71 0.4335
Disintegrating Ecosystem 1211 31.15 -2.282 56.73% 0.022 0.1329 -1.578 0.7148
Downward Spiral 2325 28.03 -2.66 61.03% 0.002 0.8492 -1.521 0.5385
Erosion of Will 1242 30.98 -2.269 51.29% -0.038 0.0075 -1.87 0.4153
Memory Fades to Dust 2358 27.52 -2.987 56.32% -0.015 0.1528 -1.728 0.5309
Promising Farmlands 1228 30.26 -2.603 53.26% -0.015 0.2813 -1.739 0.5485
Tipping Point 1147 27.17 -4.121 41.06% -0.143 0.0 -2.255 -0.0263

Results Starting on Boards

Board Completed Completion Rate Average Score Score Model Win Rate Deviation p(χ²) Win Model Differential
A 6927 62.48% 32.93 -0.269 72.48% 0.001 0.8051 -0.002 0.0707
B 6768 60.87% 32.32 -0.433 72.34% -0.006 0.3025 0.049 0.0232
C 8086 63.92% 34.09 0.245 73.39% -0.007 0.1537 0.027 -0.2103
D 7170 62.21% 33.34 0.007 74.35% 0.013 0.0105 0.038 0.0219
East 704 48.02% 46.27 2.738 71.02% 0.035 0.047 0.52 0.4785
Northeast 571 58.38% 38.23 -0.302 59.54% -0.084 0.0 -0.268 -0.2659
Northwest 609 55.36% 38.4 -0.975 65.19% -0.031 0.0984 -0.254 -0.2829
West 901 64.82% 45.53 1.277 66.93% 0.006 0.6808 -0.09 0.1699

Results Using Boards

Board Completed Completion Rate Average Score Score Model Win Rate Deviation p(χ²) Win Model Differential
A 13142 57.64% 34.08 0.054 74.66% 0.023 0.0 0.093 0.1657
B 13065 57.62% 33.83 -0.038 74.27% 0.014 0.0004 -0.033 -0.0595
C 14524 59.45% 34.49 0.287 74.82% 0.007 0.0419 0.099 -0.1386
D 13347 58.45% 33.97 -0.025 75.55% 0.025 0.0 0.113 0.0974
East 1951 55.68% 45.81 1.133 67.66% 0.001 0.8948 -0.395 -0.4373
Northeast 1829 55.73% 46.76 1.956 69.76% 0.018 0.0937 0.151 0.1526
Northwest 1785 55.3% 46.61 1.695 70.64% 0.023 0.0337 0.256 0.2273
West 1920 55.6% 45.69 0.958 67.34% 0.011 0.3232 -0.196 0.0633

Results Using Options

Option Completed Completion Rate Average Score Score Model Win Rate Deviation p(χ²) Win Model Differential
No Blight Card 820 56.9% 18.62 -6.572 67.68% -0.013 0.424 -1.093 -0.0245
Not Using Events or Tokens 3235 55.94% 24.87 -3.888 74.74% 0.024 0.002 -0.171 0.047
Skip Initial Invader Actions 1338 71.67% 45.28 3.285 87.82% 0.031 0.0017 0.742 -0.1046
Start of Game Growth 1821 67.92% 41.51 1.335 84.4% 0.01 0.2348 -0.073 -0.358
Unlimited Undo 4333 52.76% 43.18 4.694 83.38% 0.052 0.0 0.646 0.2057
Using Tokens but Not Events 3446 64.75% 28.28 -2.649 77.31% 0.006 0.3722 0.033 -0.0105

Results With Allies

Terror Level

Terror Level Completed Average Score Win Rate
I 4585 22.24 4.89%
II 7347 29.69 53.9%
III 12213 32.43 92.48%
IV 7591 36.13 99.38%

Results

Result Completed
Win: Scenario condition 339
Lose: Scenario condition 847
Lose: Adversary condition 3020
Win: Invaders destroyed 15041
Lose: Invader deck ran out 206
Win: Terror victory 7403
Win: Sacrifice victory 239
Lose: Spirit destroyed 807
Lose: Blight pool ran out 3834

Number of Players

Score Model: 0.33 Win Model: 0.087
Num. Completed Completion Rate Average Score Win Rate Dev. p(χ²)
1 14988 68.01% 32.51 70.07% -0.012 0.0007
2 8220 62.99% 32.27 72.4% -0.006 0.2524
3 3977 58.12% 35.03 77.04% 0.011 0.0999
4 4551 48.49% 41.44 77.02% 0.008 0.2049

Online Multiplayer

Score Model: -1.753 Win Model: 0.064
Multiplayer? Completed Completion Rate Average Score Win Rate
Single-Player 29991 61.18% 34.28 72.32%
Multiplayer 1745 75.94% 30.06 76.33%

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