Data analysis to verify the balance between the three races in the game StarCraft II(TM)

• Matheus Farnese Lacerda Senna UFMG
• Ana Luísa Araújo Bastos UFMG

DOI: https://doi.org/10.5753/sbgames_estendido.2023.233970

Abstract

The goal of this work is the usage of data analysis techniques, such as comparison with the multinomial distribution and the permutation test, to analyse data relative to the balance between the three races (Protoss, Terran and Zerg) from the game Starcraft II™, made by Blizzard Entertainment, Inc.. As such, said techniques were utilized to validate with 1% significance the analysis made in data from matches, tournaments and earnings, where it was verified that Zerg is better than the other two in the first two cases, but all three are well balanced when it comes to total earnings in prize money.

Keywords: StarCraft, balance, Protoss, Terran, Zerg, p-value, permutation, multinomial distribution

References

Good, Phillip I. (2012) “Introduction to statistics through resampling methods and R” John Wiley & Sons.

Adhikari, A., DeNero, J., & Wagner, D. (2022). “Computational and inferential thinking: The foundations of data science”. University of California, Berkeley.

Yun, H. (2011). “Using Logistic Regression to Analyze the Balance of a Game: The Case of StarCraft II”. arXiv preprint arXiv:1105.0755.

Ojala, M., & Garriga, G. C. (2010). “Permutation tests for studying classifier performance.” Journal of machine learning research, 11(6).

Golland, P., & Fischl, B. (2003). “Permutation tests for classification: towards statistical significance in image-based studies”. In Information Processing in Medical Imaging: 18th International Conference, IPMI 2003, Ambleside, UK, July 20-25, 2003. Proceedings 18 (pp. 330-341). Springer Berlin Heidelberg.

Mosimann, J. E. (1962). “On the compound multinomial distribution, the multivariate β-distribution, and correlations among proportions”. Biometrika, 49(1/2), 65-82.