Joint optimization of multiple responses based on loss functions

Simple item page
dc.contributor.authorErdbrügge, Martina
dc.contributor.authorKuhnt, Sonja
dc.contributor.authorRudak, Nikolaus
dc.date.accessioned2011-03-02T11:27:30Z
dc.date.available2011-03-02T11:27:30Z
dc.date.issued2011-03-02
dc.description.abstractMost of the existing methods for the analysis and optimization of multiple responses require some kind of weighting of these responses, for instance in terms of cost or desirability. Particularly at the design stage, such information is hardly available or will rather be subjective. Kuhnt and Erdbrugge (2004) present an alternative strategy using loss functions and a penalty matrix which can be decomposed into a standardizing (data-driven) and a weight matrix. The effect of different weight matrices is displayed in joint optimization plots in terms of predicted means and variances of the response variables. In this article, we propose how to choose weight matrices for two and more responses. Furthermore we prove the Pareto optimality of every point that minimizes the conditional mean of the loss function.en
dc.identifier.urihttp://hdl.handle.net/2003/27634
dc.identifier.urihttp://dx.doi.org/10.17877/DE290R-13065
dc.language.isoende
dc.relation.ispartofseriesDiscussion Paper / SFB 823 ; 10/2011
dc.subjectDifferent weight matrixen
dc.subjectLoss functionen
dc.subjectMultiple responseen
dc.subjectPareto optimalityen
dc.subjectPenalty matrixen
dc.subject.ddc310
dc.subject.ddc330
dc.subject.ddc620
dc.titleJoint optimization of multiple responses based on loss functionsen
dc.typeTextde
dc.type.publicationtypeworkingPaperde
dcterms.accessRightsopen access

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
DP_1011_SFB823_Erdbrügge_Kuhnt_Rudak.pdf
Size:
753.2 KB
Format:
Adobe Portable Document Format
Description:
DNB
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1018 B
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Sonderforschungsbereich (SFB) 823