An optimal strategy for sequential classification on partially ordered sets
A decision-theoretic framework is described for sequential classification when the parameter space is a finite partially ordered set. An example of an optimal strategy is then presented. This example establishes that an asymptotically optimal class of experiment selection rules is not necessarily optimal in the given decision-theoretic setting.
Year of publication: |
2004
|
---|---|
Authors: | Ferguson, S. ; Thomas, T. ; Tatsuoka, Curtis |
Published in: |
Statistics & Probability Letters. - Elsevier, ISSN 0167-7152. - Vol. 68.2004, 2, p. 161-168
|
Publisher: |
Elsevier |
Keywords: | Sequential selection of experiment Group testing Cognitively diagnostic educational testing Decision theory |
Saved in:
Saved in favorites
Similar items by person
-
Ferguson, S., (2012)
-
Lumbar spine forces during manoeuvring of ceiling-based and floor-based patient transfer devices
Marras, W.S., (2009)
-
Latent Partially Ordered Classification Models and Normal Mixtures
Tatsuoka, Curtis, (2013)
- More ...