Name
Title | ||
|---|---|---|
Automated Empirical Selection of Rule Induction Methods Based on Recursive Iteration of Resampling Methods and Multiple Testing |
Abstract | ||
|---|---|---|
This paper proposes a method for multiple testing based on recursive iteration of resampling methods for rule induction. The method generates training samples and test samples in a two-level hierarchical way, and compared the results between these two levels, which corresponding to second-order approximation of estimators in Edge worth expansion. We applied this MULT-RECITE-R method to three newly collected medical databases and seven UCI databases. The results show that this method gives the best selection of estimation methods in almost the all cases. |
Year | DOI | Venue |
|---|---|---|
2010 | 10.1109/ICDMW.2010.177 | ICDM Workshops |
Keywords | Field | DocType |
multiple testing,medical databases,uci databases,recursive iteration,estimation method,resampling method,mult-recite-r method,best selection,resampling methods,edge worth expansion,rule induction,automated empirical selection,approximation theory,resampling,databases,edgeworth expansion,measurement,estimation,sampling methods,mathematical model,second order approximation | Data mining,Edgeworth series,Computer science,Approximation theory,Multiple comparisons problem,Sampling (statistics),Rule induction,Artificial intelligence,Resampling,Machine learning,Recursion,Estimator | Conference |
Citations | PageRank | References |
1 | 0.35 | 2 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Shusaku Tsumoto | 1 | 1820 | 294.19 |
| Shoji Hirano | 2 | 560 | 99.17 |