Please use this identifier to cite or link to this item: 
Year of Publication: 
Series/Report no.: 
Technical Report No. 2004,19
Universität Dortmund, Sonderforschungsbereich 475 - Komplexitätsreduktion in Multivariaten Datenstrukturen, Dortmund
For the problem of percentile estimation of a quantal response curve, we determine multi-objective designs which are robust with respect to misspecifications of the model assumptions. We propose a maximin approach based on efficiencies and provide designs that are simultaneously efficient with respect to the particular choice of various parameter regions and link functions. Furthermore, we deal with the problems of designing model and percentile robust experiments and give various examples of such designs, which are calculated numerically.
Binary response model
robust optimal design
percentile estimation
multi-objective designs
Document Type: 
Working Paper

Files in This Item:
180.12 kB
344.8 kB

Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.