Validating the win-rate of heroes in Dota 2 using instrumental variable estimation

Validating the win-rate of heroes in Dota 2 using instrumental variable estimation

van der Maas, David (TU Delft Electrical Engineering, Mathematics and Computer Science)

Krijthe, J.H. (mentor)
Karlsson, R.K.A. (graduation committee)

Delft University of Technology

Computer Science and Engineering

CSE3000 Research Project

2022-06-24

This research provides additional insights in to when instrumental variable estimation is a proper method to use when investigating or removing causal effects in randomized experiments. this is done by using instrumental variables on the game Dota 2, in which win-rates of a couple heroes are validated and reviewed to test the effectiveness and usefulness of instrumental variables. The results show mixed signs, for such a complex statistical game with many confounding factors, getting a good variable to work is hard. In the end it is concluded that Dota 2 with its randomized game-mode of single draft is still a too complex experiment to retrieve unbiased results from the instrumental variable estimation method. Therefore it is not advised to use this method in a setting where the environment is is too complex.

IV
Instrumental Variable
DotA 2
Causal Inference

http://resolver.tudelft.nl/uuid:c04d0f4b-14fc-4d65-9756-0cf3abec54c9

Student theses

bachelor thesis

© 2022 David van der Maas