Dear All,
Below is a summary of the responses to the original request for information
on Multidimensional Scaling. Paper.doc mentioned in 1. is not attached.
Many thanks to all who responded.
Lynn
CTI Statistics
****************************************************************************
*****************************
1. We have recently applied the marginal likelihood
Kalbfleisch, JD; Prentice, RL (1973)
Marginal likelihoods based on Cox's regression and life model.
Biometrika 60: 267-278
and obtained a generalization of the log-rank test to multivariate ordinal
data:
Susser, E; Desvarieux, M; Wittkowski, KM (1998)
Reporting sexual risk behavior for HIV:
a practical risk index and a method for improving risk indices.
American Journal of Public Health 88: 671-674
If you have no "a-posteriori" marker to validate the multivariate
"a-priori" markers, it is even more simple than the case considered in
Susser et al. (1998), so you may skip the "a-posteriori" ranking
(seroconversion) and use the method as originally proposed:
Wittkowski, KM (1992)
An extension to Wittkowski.
Journal of the American Statistical Association 87: 258
Attachment Converted: "c:\program files\eudora\attach\Paper.doc"
Knut M. Wittkowski, PhD,DSc e-mail: [log in to unmask]
2. Try "The Analysis of Proximity Data" Everitt and Rabe-Hesketh, published
by Arnold 1997
Professor Brian Everitt
[log in to unmask]
3. A useful book may be 'Multidimensional Scaling' by TF Cox & MAA Cox (1994)
4. You can try this reference:
Introduction to multivariate analysis. By Chatfield C. & Collin AJ.
[Chapman and Hall]
Ly-Mee (Ms.)
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|