TY - GEN
T1 - Selection of Morris trajectories for initial sensitivity analysis
AU - Norton, John P.
PY - 2009
Y1 - 2009
N2 - The Morris method of initial sensitivity analysis of large models varies factors singly along a few trajectories. Its nominally uniform coverage of the factors may deviate greatly from uniform in such small samples. Campolongo et al. suggest selecting a subset of trajectories from a large set, to maximise their spread. Ways to reduce the computing demand of this procedure are examined, including alternative distance measures and two-stage selection. An example with more economical selection is used to investigate how the factors' marginal distributions deviate from uniform on trajectories selected by spread or by the number of factors whose values differ between trajectories.
AB - The Morris method of initial sensitivity analysis of large models varies factors singly along a few trajectories. Its nominally uniform coverage of the factors may deviate greatly from uniform in such small samples. Campolongo et al. suggest selecting a subset of trajectories from a large set, to maximise their spread. Ways to reduce the computing demand of this procedure are examined, including alternative distance measures and two-stage selection. An example with more economical selection is used to investigate how the factors' marginal distributions deviate from uniform on trajectories selected by spread or by the number of factors whose values differ between trajectories.
KW - Parametric variation
KW - Perturbed coefficients
KW - Sensitivity analysis
KW - Validation
UR - http://www.scopus.com/inward/record.url?scp=80051656296&partnerID=8YFLogxK
U2 - 10.3182/20090706-3-FR-2004.0431
DO - 10.3182/20090706-3-FR-2004.0431
M3 - Conference contribution
SN - 9783902661470
T3 - IFAC Proceedings Volumes (IFAC-PapersOnline)
SP - 670
EP - 674
BT - 15th Symposium on System Identification, SYSID 2009 - Preprints
T2 - 15th IFAC Symposium on System Identification, SYSID 2009
Y2 - 6 July 2009 through 8 July 2009
ER -