A note on the relation between local power and robustness to misspecification

A simple example is provided that shows that one test can strictly dominate another test in both local power and its robustness to asymptotic size distortion under local model misspecification, with both tests having asymptotic size equal to nominal size under correct model specification. Robustness...

Full description

Saved in:
Bibliographic Details
Published inEconomics letters Vol. 116; no. 2; pp. 133 - 135
Main Author Guggenberger, Patrik
Format Journal Article
LanguageEnglish
Published Amsterdam Elsevier B.V 01.08.2012
Elsevier Science Ltd
Subjects
Online AccessGet full text

Cover

Loading…
More Information
Summary:A simple example is provided that shows that one test can strictly dominate another test in both local power and its robustness to asymptotic size distortion under local model misspecification, with both tests having asymptotic size equal to nominal size under correct model specification. Robustness of the asymptotic size to model misspecification is therefore an alternative criterion to choosing among competing tests that can offer additional discriminatory insight over local power. ► Suggest using size-robustness under local model misspecification to choose among tests. ► One test can strictly dominate another test in both local power and size-robustness. ► Thus, size-robustness can offer additional discriminatory insight over local power.
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISSN:0165-1765
1873-7374
DOI:10.1016/j.econlet.2012.01.020