This paper considers a nonparametric time series regression model with a nonstationary regressor. We construct a nonparametric test for testing whether the regression is of a known parametric form indexed by a vector of unknown parameters. We establish the asymptotic distribution of the proposed...

Since the parameters of an autoregressive conditional heteroskedasticity (ARCH) process must be non-negative, inference on ARCH parameters can be improved by using inequality constrained estimation. In this paper, we extend this principle to the problem of ARCH lag order selection. We show that...