RT Generic
T1 Non-parametric specification testing of non-nested econometric models
A1 Delgado, Miguel A.
A1 Li, Qi
A1 Stengos, Thanasis
A2 Universidad Carlos III de Madrid. Departamento de Estadística, 
AB We consider the non-nested testing prqblem of non-parametric regressions. We show that, when the regression functions are unknown under both the null and the alternative hypotheses, an extension of the J-test procedure of Davidson and Mackinnon (1981) will lead to a test statistic with well defined asymptotic properties. The derivation of the test statistic involves double kernel estimation. Monte Carlo simulations suggest that the test has good size and power characteristics.
YR 1994
FD 1994-12
LK https://hdl.handle.net/10016/3961
UL https://hdl.handle.net/10016/3961
LA eng
DS e-Archivo
RD 7 may. 2024