A model specification test for the variance function in nonparametric regression

Pardo Fernández, Juan Carlos; Jiménez Gamero, María Dolores

Abstract:

The problem of testing for the parametric form of the conditional variance is considered in a fully nonparametric regression model. A test statistic based on a weighted L2-distance between the empirical characteristic functions of residuals constructed under the null hypothesis and under the alternative is proposed and studied theoretically. The null asymptotic distribution of the test statistic is obtained and employed to approximate the critical values. Finite sample properties of the proposed test are numerically investigated in several Monte Carlo experiments. The developed results assume independent data. Their extension to dependent observations is also discussed.

Year:

2019

Type of Publication:

Article

Keywords:

Characteristic function; Conditional variance models; Nonparametric regression; Regression residuals

Journal:

AStA Advances in Statistical Analysis

Month:

In press

Note:

Q4 99/123 h-index 0,643 (JCR2018)

Comments:

MTM2014-55966-P and MTM2017-89422-P

DOI:

https://doi.org/10.1007/s10182-018-00336-y