%0 Conference Paper %1 PetitjeanEtAl14a %A Petitjean, F. %A Allison, L. %A Webb, G.I. %B Proceedings of the 14th IEEE International Conference on Data Mining %D 2014 %K Association Discovery, Rule discovery, graphical models scalable sound statistically %P 480-489 %T A Statistically Efficient and Scalable Method for Log-Linear Analysis of High-Dimensional Data %U http://dx.doi.org/10.1109/ICDM.2014.23 %X Log-linear analysis is the primary statistical approach to discovering conditional dependencies between the variables of a dataset. A good log-linear analysis method requires both high precision and statistical efficiency. High precision means that the risk of false discoveries should be kept very low. Statistical efficiency means that the method should discover actual associations with as few samples as possible. Classical approaches to log-linear analysis make use of χ2 tests to control this balance between quality and complexity. We present an information-theoretic approach to log-linear analysis. We show that our approach 1) requires significantly fewer samples to discover the true associations than statistical approaches -- statistical efficiency -- 2) controls for the risk of false discoveries as well as statistical approaches -- high precision - and 3) can perform the discovery on datasets with hundreds of variables on a standard desktop computer -- computational efficiency.

@inproceedings{PetitjeanEtAl14a, abstract = {Log-linear analysis is the primary statistical approach to discovering conditional dependencies between the variables of a dataset. A good log-linear analysis method requires both high precision and statistical efficiency. High precision means that the risk of false discoveries should be kept very low. Statistical efficiency means that the method should discover actual associations with as few samples as possible. Classical approaches to log-linear analysis make use of χ2 tests to control this balance between quality and complexity. We present an information-theoretic approach to log-linear analysis. We show that our approach 1) requires significantly fewer samples to discover the true associations than statistical approaches -- statistical efficiency -- 2) controls for the risk of false discoveries as well as statistical approaches -- high precision - and 3) can perform the discovery on datasets with hundreds of variables on a standard desktop computer -- computational efficiency.}, added-at = {2016-03-20T05:42:04.000+0100}, author = {Petitjean, F. and Allison, L. and Webb, G.I.}, biburl = {https://www.bibsonomy.org/bibtex/251ae580872208cf345e8f42c80587089/giwebb}, booktitle = {Proceedings of the 14th {IEEE} International Conference on Data Mining}, interhash = {9540e432b3e876e3852e3912112f4ec4}, intrahash = {51ae580872208cf345e8f42c80587089}, keywords = {Association Discovery, Rule discovery, graphical models scalable sound statistically}, pages = {480-489}, timestamp = {2016-03-20T05:42:04.000+0100}, title = {A Statistically Efficient and Scalable Method for Log-Linear Analysis of High-Dimensional Data}, url = {http://dx.doi.org/10.1109/ICDM.2014.23}, year = 2014 }