The idea of specious rules and their detection is explained in the paper W. Hämäläinen and G. Webb: Specious rules: an efficient and effective unifying method for removing misleading and uninformative patterns in association rule mining. Proceedings of SIAM International Conference on Data Mining, pp. 309-317, SIAM 2017 Updated version of the paper (minor corrections).
slides of the SDM'17 presentation
Coping with Yule-Simpson's paradox and other specious associations - a short tutorial in WiDS 2018 Helsinki
This is a version of the Kingfisher program with special filtering of specious association rules. The current version supports only Mutual information measure. This version is for studying speciousness and therefore it outputs very detailed information on specious rules and speciousness testing.