The Solution of the Metric STRESS and SSTRESS Problems in Multidimensional Scaling Using Newton's Method

dc.contributor.authorKearsley, A.J.
dc.contributor.authorTapia, R.A.
dc.contributor.authorTrosset, M.W.
dc.date.accessioned2018-06-18T17:41:51Z
dc.date.available2018-06-18T17:41:51Z
dc.date.issued1994-12
dc.date.noteDecember 1994
dc.description.abstractThis paper considers numerical algorithms for finding local minimizers of metric multidimensional scaling problems. The two most common optimality criteria (STRESS and SSTRESS) are considered, the leading algorithms for each are carefully explicated, and a new algorithm is proposed. The new algorithm is based on Newton's method and relies on a parameterization that has not previously been used in multidimensional scaling algorithms. In contrast to previous algorithms, a very pleasant feature of the new algorithm is that it can be used with either the STRESS or the SSTRESS criterion. Numerical results are presented for the metric STRESSS problem. These results are quite satisfying and, among other things, suggest that the well-known SMACOF-I algorithm tends to stop prematurely.
dc.format.extent24 pp
dc.identifier.citationKearsley, A.J., Tapia, R.A. and Trosset, M.W.. "The Solution of the Metric STRESS and SSTRESS Problems in Multidimensional Scaling Using Newton's Method." (1994) <a href="https://hdl.handle.net/1911/101849">https://hdl.handle.net/1911/101849</a>.
dc.identifier.digitalTR94-44
dc.identifier.urihttps://hdl.handle.net/1911/101849
dc.language.isoeng
dc.titleThe Solution of the Metric STRESS and SSTRESS Problems in Multidimensional Scaling Using Newton's Method
dc.typeTechnical report
dc.type.dcmiText
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
TR94-44.pdf
Size:
509.43 KB
Format:
Adobe Portable Document Format