Testing Constancy in Varying Coefficient Models

This article proposes a coefficient constancy test in semi-varying coe¢ cient models, which only needs to estimate the restricted coefficients under the null hypothesis. The test statistic resembles the union-intersection test after ordering the data according to the varying coefficients' expla...

ver descrição completa

Detalhes bibliográficos
Autores: Delgado, M.A., Arteaga Molina, Luis Antonio|||0000-0002-1721-0720
Formato: artículo
Fecha de publicación:2021
País:España
Recursos:Universidad de Cantabria (UC)
Repositorio:UCrea Repositorio Abierto de la Universidad de Cantabria
Idioma:inglés
OAI Identifier:oai:repositorio.unican.es:10902/23945
Acesso em linha:http://hdl.handle.net/10902/23945
Access Level:acceso abierto
Palavra-chave:Varying coefficient models
Model checks
UI tests
Concomitants
Partial effects model checks
Wild bootstrap
Trimming data-driven calibration
Descrição
Resumo:This article proposes a coefficient constancy test in semi-varying coe¢ cient models, which only needs to estimate the restricted coefficients under the null hypothesis. The test statistic resembles the union-intersection test after ordering the data according to the varying coefficients' explanatory variable. This statistic depends on a trimming parameter that can be chosen by the data-driven calibration method we propose. A bootstrap test is justified under fairly general regularity conditions. Under more restrictive assumptions, the critical values can be tabulated, and trimming is unnecessary. The proposed test can be applied to specification testing of partial effects in the direction of non(semi)-parametric alternatives. The finite sample performance is studied by means of Monte Carlo experiments, and a real data application for modelling education returns.