Testing the concavity of an ordinaldominance curve
We study the asymptotic properties of a class of statistics used for testing the null hypothesis that an ordinal dominance curve is concave. The statistics are based on the Lp-distance between the empirical ordinal dominance curve and its least concave majo- rant, with 1 â‰¤ p â‰¤ âˆž. We formally establish the limit distribution of the statistics when the true ordinal dominance curve is concave. Further, we establish that, when 1 â‰¤ p â‰¤ 2, the limit distribution is stochastically largest when the true ordinal dominance curve is the 45-degree line. When p > 2, this is not the case, and in fact the limit distribution diverges to infinity along a suitably chosen sequence of concave ordinal dominance curves. Our results serve to clarify, extend and amend assertions appearing previously in the literature for the cases p = 1 and p = âˆž.
|Date of creation:||02 Apr 2012|
|Date of revision:|
|Contact details of provider:|| Postal: |
Phone: (858) 534-3383
Fax: (858) 534-7040
Web page: http://www.escholarship.org/repec/ucsdecon/
More information through EDIRC
References listed on IDEAS
Please report citation or reference errors to , or , if you are the registered author of the cited work, log in to your RePEc Author Service profile, click on "citations" and make appropriate adjustments.:
- Christopher A. Carolan & Joshua M. Tebbs, 2005. "Nonparametric tests for and against likelihood ratio ordering in the two-sample problem," Biometrika, Biometrika Trust, vol. 92(1), pages 159-171, March.
- Beare, Brendan K., 2011. "Measure preserving derivatives and the pricing kernel puzzle," Journal of Mathematical Economics, Elsevier, vol. 47(6), pages 689-697.
When requesting a correction, please mention this item's handle: RePEc:cdl:ucsdec:qt6qg1f8ms. 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: (Lisa Schiff)
If references are entirely missing, you can add them using this form.