Authors: Morik, Katharina
Pumplün, Constanze
Rüping, Stefan
Weihs, Claus
Title: D-optimal plans in observational studies
Language (ISO): en
Abstract: This paper investigates the use of Design of Experiments in observational studies in order to select informative observations and features for classification. D-optimal plans are searched for in existing data and based on these plans the variables most relevant for classification are determined. The adapted models are then compared with respect to their predictive accuracy on an independent test sample. Eight different data sets are investigated by this method.
Subject Headings: D-optimality
Feature Selection
Genetic Algorithm
Prototypes
URI: http://hdl.handle.net/2003/21668
http://dx.doi.org/10.17877/DE290R-14490
Issue Date: 2005-11-07T11:40:01Z
Appears in Collections:Sonderforschungsbereich (SFB) 475

Files in This Item:
File Description SizeFormat 
tr44-05.pdfDNB157.72 kBAdobe PDFView/Open


This item is protected by original copyright



This item is protected by original copyright rightsstatements.org