Robust optimal designs to a misspecified model

Chiara Tommasi
Additional contact information
Chiara Tommasi: University of Milano

No unimi-1078, UNIMI - Research Papers in Economics, Business, and Statistics from Universitá degli Studi di Milano

Abstract: Usually, in the Theory of Optimal Experimental Design the model is assumed to be known at the design stage. In practice, however, more competing models may be plausible for the same data. Thus, a possibility is to find an optimal design which take both model discrimination and parameter estimation into consideration. In this paper we follow a different approach: we find a design which is optimum for estimation purposes but is also robust to a misspecified model. In other words, the optimum design is "good" for estimating the unknown parameters even if the assumed model is not correct.

Keywords: D-optimality; information sandwich variance matrix; maximum likelihood estimator (search for similar items in EconPapers)
Date: 2008-09-23
Note: oai:cdlib1:unimi-1078
References: Add references at CitEc
Citations:

Downloads: (external link)
http://services.bepress.com/unimi/statistics/art37 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:bep:unimip:unimi-1078

Access Statistics for this paper

More papers in UNIMI - Research Papers in Economics, Business, and Statistics from Universitá degli Studi di Milano Contact information at EDIRC.
Bibliographic data for series maintained by Christopher F. Baum ().