Please use this identifier to cite or link to this item: http://hdl.handle.net/10525/1201

 Title: Methods of Regularities Searching Based on Optimal Partitioning Authors: Senko, OlegKuznetsova, Anna Keywords: Optimal PartitioningStatistical ValidityPermutation TestRegularitiesExplanatory Variables EffectComplexityProbability and StatisticsData Mining Issue Date: 2009 Publisher: Institute of Information Theories and Applications FOI ITHEA Abstract: The purpose of discussed optimal valid partitioning (OVP) methods is uncovering of ordinal or continuous explanatory variables effect on outcome variables of different types. The OVP approach is based on searching partitions of explanatory variables space that in the best way separate observations with different levels of outcomes. Partitions of single variables ranges or two-dimensional admissible areas for pairs of variables are searched inside corresponding families. Statistical validity associated with revealed regularities is estimated with the help of permutation test repeating search of optimal partition for each permuted dataset. Method for output regularities selection is discussed that is based on validity evaluating with the help of two types of permutation tests. URI: http://hdl.handle.net/10525/1201 ISSN: 1313-0455 Appears in Collections: Book 08 Classification Forecasting Data Mining

Files in This Item:

File Description SizeFormat