A minimax equivalence theorem for optimum bounded design measures
For [mu] a given measure and [phi](Â·) a regular optimality criterion, function of the information matrix, we consider [phi]-optimum design measures [xi][alpha]* that maximise [phi] under the constraint [xi][alpha]*[less-than-or-equals, slant][mu]/[alpha], [alpha] given in (0,1). We derive an equivalence theorem of the minimax form for this design problem, show that the optimum criterion value [phi][alpha]*=[phi]([xi][alpha]*) is continuous in [alpha] and give a condition for [phi][alpha]* being differentiable with respect to [alpha].
Volume (Year): 68 (2004)
Issue (Month): 4 (July)
|Contact details of provider:|| Web page: http://www.elsevier.com/wps/find/journaldescription.cws_home/622892/description#description|
|Order Information:|| Postal: http://www.elsevier.com/wps/find/supportfaq.cws_home/regional|
When requesting a correction, please mention this item's handle: RePEc:eee:stapro:v:68:y:2004:i:4:p:325-331. See general information about how to correct material in RePEc.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (Dana Niculescu)
If references are entirely missing, you can add them using this form.