A comparison of statistical significance tests for information retrieval evaluation.

@inproceedings{smucker-2007-comparison, author = {Mark D. Smucker and James Allan and Ben Carterette}, editor = {M\'{a}rio J. Silva and Alberto H. F. Laender and Ricardo Baeza-Yates and Deborah L. McGuinness and Bj{\o}rn Olstad and {\O}ystein Haug Olsen and Andr\'{e} O. Falc\~{a}o}, title = {{A comparison of statistical significance tests for information retrieval evaluation}}, booktitle = {{Proceedings of the Sixteenth ACM Conference on Information and Knowledge Management, CIKM 2007, Lisbon, Portugal, November 6-10, 2007}}, pages = {623--632}, publisher = {ACM}, year = {2007}, url = {https://doi.org/10.1145/1321440.1321528}, doi = {https://doi.org/10.1145/1321440.1321528} }