Computing D-optimal experimental designs for estimating treatment contrasts under the presence of a nuisance time trend

Please always quote using this URN: urn:nbn:de:0297-zib-53640
  • We prove a mathematical programming characterisation of approximate partial D-optimality under general linear constraints. We use this characterisation with a branch-and-bound method to compute a list of all exact D-optimal designs for estimating a pair of treatment contrasts in the presence of a nuisance time trend up to the size of 24 consecutive trials.

Download full text files

Export metadata

Metadaten
Author:Radoslav Harman, Guillaume Sagnol
Document Type:ZIB-Report
Tag:branch and bound; nuisance trend; optimal design of experiments
MSC-Classification:62-XX STATISTICS
90-XX OPERATIONS RESEARCH, MATHEMATICAL PROGRAMMING
Date of first Publication:2015/12/02
Series (Serial Number):ZIB-Report (15-02)
ISSN:1438-0064
Published in:Appeared in: Stochastic Models, Statistics and Their ApplicationsSpringer Proceedings in Mathematics & Statistics Volume 122, 2015, pp 83-91
DOI:https://doi.org/10.1007/978-3-319-13881-7_10