Statistical Significance Testing in Information Retrieval: An Empirical Analysis of Type I, Type II and Type III Errors.

@inproceedings{urbano-2019-statistical, author = {Juli\'{a}n Urbano and Harlley Lima and Alan Hanjalic}, editor = {Benjamin Piwowarski and Max Chevalier and \'{E}ric Gaussier and Yoelle Maarek and Jian-Yun Nie and Falk Scholer}, title = {{Statistical Significance Testing in Information Retrieval: An Empirical Analysis of Type I, Type II and Type III Errors}}, booktitle = {{Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2019, Paris, France, July 21-25, 2019}}, pages = {505--514}, publisher = {ACM}, year = {2019}, url = {https://doi.org/10.1145/3331184.3331259}, doi = {https://doi.org/10.1145/3331184.3331259} }