On the Statistical Comparison of Inductive Learning Methods

On the Statistical Comparison of Inductive Learning Methods (1996)

Cached

Download Links

[www.vuse.vanderbilt.edu]

by A. Feelders , W. Verkooijen

Venue:	In D. Fisher & H.-J. Lenz (Eds.), Learning from Data: Artificial and Intelligence V
Citations:	5 - 0 self

Versions

Version History

Metadata Version 3

User correction supplied by SystemCorrections

Datum	Value	Source
TITLE	On the Statistical Comparison of Inductive Learning Methods	INFERENCE
AUTHOR NAME	A. Feelders	SVM HeaderParse 0.1
AUTHOR AFFIL	y	SVM HeaderParse 0.2
AUTHOR NAME	W. Verkooijen	SVM HeaderParse 0.1
AUTHOR AFFIL	yy; University of Twente; y; Department of Computer Science	SVM HeaderParse 0.2
AUTHOR ADDR	P.O.Box 217, 7500 AE Enschede; The Netherlands	SVM HeaderParse 0.1
ABSTRACT	Experimental comparisons between statistical and machine learning methods appear with increasing frequency in the literature. However, there does not seem to be a consensus on how such a comparison is performed in a methodologically sound way. Especially the effect of testing multiple hypotheses on the probability of producing a "false alarm" is often ignored. We transfer multiple comparison procedures from the statistical literature to the type of study discussed in this paper. These testing procedures take the number of tests performed into account, thereby controlling the probability of generating "false alarms". The multiple comparison procedures selected are illustrated on well-known regression and classification data sets. 26.1 Introduction Recent interactions between the statistical and artificial intelligence communities (see e.g. [Han93, CO94]), have led to many studies that compare the performance of empirical statistical and machine learning methods on real-life data sets; ...	user correction - Legacy Corrections
YEAR	1996	INFERENCE
VENUE	In D. Fisher & H.-J. Lenz (Eds.), Learning from Data: Artificial and Intelligence V	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
PAGES	271--279	INFERENCE
CITATIONS	21 found	ParsCit 1.0