Results vs. Adversaries

Adversary Completed Completion Rate Average Score Score Model Win Rate Deviation p(χ²) Win Model Differential
The Kingdom of Brandenburg-Prussia 6490 61.12% 38.1 6.388 75.22% 0.039 0.0 -0.316 0.1176
The Kingdom of England 4452 55.11% 33.76 3.632 56.33% -0.064 0.0 -1.264 0.0544
The Kingdom of France (Plantation Colony) 3128 61.32% 34.1 3.142 42.49% -0.155 0.0 -2.099 -0.3188
The Kingdom of Sweden 3516 57.53% 32.48 3.003 69.06% -0.018 0.0172 -0.582 -0.0773

Results in Scenarios

Scenario Difficulty Completed Completion Rate Average Score Score Model Win Rate Deviation p(χ²) Win Model Differential
Blitz 0 381 59.91% 24.8 -2.37 63.78% -0.046 0.0556 -0.452 0.012
Dahan Insurrection 4 458 56.54% 48.55 8.535 62.66% -0.058 0.0077 -1.044 -0.6953
Guard the Isle's Heart 0 1248 68.09% 37.73 2.937 64.42% -0.091 0.0 -0.949 -0.6426
Powers Long Forgotten 1 167 44.89% 31.65 0.372 66.47% -0.041 0.2444 0.018 0.3203
Rituals of Terror 3 151 42.18% 31.56 0.343 45.7% -0.19 0.0 -0.916 -0.2463
Rituals of the Destroying Flame 3 100 39.37% 32.57 0.464 51.0% -0.095 0.0527 -0.777 -0.0712
Second Wave 0 1543 58.36% 28.91 -0.535 71.61% 0.014 0.238 -0.438 0.017
Ward the Shores 2 127 43.79% 29.13 -1.256 44.09% -0.184 0.0 -1.143 -0.1703

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 1261 29.48 -1.096 54.08% -0.031 0.0266 -1.972 0.1571
Aid From Lesser Spirits 1048 30.88 -0.43 56.3% -0.033 0.0272 -1.86 0.1323
Back Against the Wall 1070 30.17 -0.767 54.02% -0.033 0.0297 -1.966 0.1777
Disintegrating Ecosystem 1271 27.64 -2.077 52.48% -0.021 0.1377 -2.03 0.2634
Downward Spiral 3609 25.25 -2.022 64.37% 0.036 0.0 -1.789 0.2698
Erosion of Will 1209 28.01 -1.769 51.03% -0.04 0.0052 -2.112 0.1732
Memory Fades to Dust 3673 24.12 -2.574 58.45% 0.007 0.3805 -2.066 0.193
Promising Farmlands 1347 28.62 -1.458 56.35% 0.016 0.2415 -1.9 0.3874
Tipping Point 1196 28.33 -1.619 52.42% -0.029 0.0425 -2.055 0.1735

Results Starting on Boards

Board Completed Completion Rate Average Score Score Model Win Rate Deviation p(χ²) Win Model Differential
A 6625 55.82% 27.45 -0.415 69.6% -0.014 0.013 0.059 0.1319
B 6894 62.04% 28.32 -0.281 71.03% -0.013 0.0187 -0.075 -0.1014
C 6688 61.81% 28.19 -0.268 70.92% -0.029 0.0 -0.095 -0.3323
D 7033 63.62% 30.1 0.494 73.24% 0.007 0.1724 0.082 0.066
East 463 52.38% 39.3 1.823 62.42% -0.05 0.0221 -0.082 -0.1237
Northeast 485 50.89% 40.73 2.336 68.45% 0.006 0.7625 0.125 0.1265
Northwest 408 56.2% 37.01 1.107 63.24% -0.049 0.0324 0.279 0.2504
West 451 50.5% 34.15 -0.104 51.66% -0.145 0.0 -0.274 -0.0142

Results Using Boards

Board Completed Completion Rate Average Score Score Model Win Rate Deviation p(χ²) Win Model Differential
A 11214 55.16% 28.8 -0.447 70.51% -0.005 0.2674 -0.096 -0.0229
B 11416 55.46% 29.69 0.166 71.98% -0.003 0.4419 0.157 0.1307
C 11435 55.66% 29.76 0.201 71.99% -0.019 0.0 0.177 -0.0603
D 11901 56.84% 30.66 0.661 72.92% 0.004 0.3234 0.078 0.0616
East 1139 49.78% 40.04 1.915 61.46% -0.059 0.0 -0.015 -0.057
Northeast 977 50.65% 40.32 1.618 65.51% -0.023 0.1229 0.063 0.0649
Northwest 902 51.48% 38.16 0.453 61.53% -0.066 0.0 -0.225 -0.2542
West 1072 49.72% 37.67 0.442 57.93% -0.083 0.0 -0.066 0.1932

Results Using Options

Option Completed Completion Rate Average Score Score Model Win Rate Deviation p(χ²) Win Model Differential
No Blight Card 1412 52.34% 16.56 -5.556 59.56% -0.092 0.0 -1.368 -0.2994
Not Using Events or Tokens 7219 59.61% 23.29 -2.541 73.97% 0.03 0.0 0.01 0.2277
Skip Initial Invader Actions 964 61.05% 35.06 2.612 86.1% 0.014 0.2239 0.81 -0.0369
Start of Game Growth 1237 62.04% 33.12 1.319 83.75% 0.004 0.6882 0.149 -0.1361
Unlimited Undo 2944 47.44% 34.17 2.437 77.04% -0.011 0.1446 0.31 -0.1306
Using Tokens but Not Events 2745 58.11% 26.66 -1.316 74.21% -0.024 0.0036 0.072 0.0288

Results With Allies

Terror Level

Terror Level Completed Average Score Win Rate
I 1510 22.24 1.85%
II 5311 29.69 18.87%
III 8768 32.43 69.55%
IV 13458 36.13 99.47%

Results

Result Completed
Win: Scenario condition 342
Lose: Scenario condition 400
Lose: Adversary condition 2042
Win: Invaders destroyed 6772
Lose: Invader deck ran out 32
Win: Terror victory 13310
Win: Sacrifice victory 90
Lose: Spirit destroyed 346
Lose: Blight pool ran out 5713

Number of Players

Score Model: 0.307 Win Model: 0.073
Num. Completed Completion Rate Average Score Win Rate Dev. p(χ²)
1 16301 68.19% 27.62 70.95% 0.003 0.4817
2 7271 56.65% 28.88 67.89% -0.045 0.0
3 2687 50.42% 31.73 72.05% -0.038 0.0
4 2788 44.68% 35.96 74.46% -0.016 0.0418

Online Multiplayer

Score Model: -1.405 Win Model: -0.013
Multiplayer? Completed Completion Rate Average Score Win Rate
Single-Player 27412 59.49% 29.24 70.58%
Multiplayer 1635 73.19% 27.11 71.38%

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