TY - JOUR
T1 - A new robust and most powerful test in the presence of local misspecification
AU - Bera, Anil K.
AU - Montes-Rojas, Gabriel
AU - Sosa-Escudero, Walter
N1 - Publisher Copyright:
© 2017 Taylor & Francis Group, LLC.
PY - 2017/8/18
Y1 - 2017/8/18
N2 - This article proposes a new test that is consistent, achieves correct asymptotic size, and is locally most powerful under local misspecification, and when any √n-estimator of the nuisance parameters is used. The new test can be seen as an extension of the Bera and Yoon (1993) procedure that deals with non maximum likelihood (ML) estimation, while preserving its optimality properties. Similarly, the proposed test extends Neyman's (1959) C(α) test to handle locally misspecified alternatives. A Monte Carlo study investigates the finite sample performance in terms of size, power, and robustness to misspecification.
AB - This article proposes a new test that is consistent, achieves correct asymptotic size, and is locally most powerful under local misspecification, and when any √n-estimator of the nuisance parameters is used. The new test can be seen as an extension of the Bera and Yoon (1993) procedure that deals with non maximum likelihood (ML) estimation, while preserving its optimality properties. Similarly, the proposed test extends Neyman's (1959) C(α) test to handle locally misspecified alternatives. A Monte Carlo study investigates the finite sample performance in terms of size, power, and robustness to misspecification.
KW - Local misspecification
KW - Neyman's C(α)
KW - Rao's score test
KW - specification testing
UR - http://www.scopus.com/inward/record.url?scp=85018175868&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85018175868&partnerID=8YFLogxK
U2 - 10.1080/03610926.2016.1177077
DO - 10.1080/03610926.2016.1177077
M3 - Article
AN - SCOPUS:85018175868
SN - 0361-0926
VL - 46
SP - 8187
EP - 8198
JO - Communications in Statistics - Theory and Methods
JF - Communications in Statistics - Theory and Methods
IS - 16
ER -