Linear Serial Rank Tests for Randomness Against Arma Alternatives
TLDR
In this article, a class of linear serial rank statistics for the problem of testing white noise against alternatives of ARMA serial dependence is introduced, and the efficiency properties of the proposed statistics are investigated, and an explicit formulation of the asymptotically most efficient score-generating functions is provided.Abstract:
In this paper we introduce a class of linear serial rank statistics for the problem of testing white noise against alternatives of ARMA serial dependence. The asymptotic normality of the proposed statistics is established, both under the null as well as alternative hypotheses, using LeCam's notion of contiguity. The efficiency properties of the proposed statistics are investigated, and an explicit formulation of the asymptotically most efficient score-generating functions is provided. Finally, we study the asymptotic relative efficiency of the proposed procedures with respect to their normal theory counterparts based on sample autocorrelations.read more
Citations
More filters
MonographDOI
Modelling nonlinear economic time series
TL;DR: In this article, the authors propose a non-parametric approach for estimating parametric models from state space models and nonlinear and non-stationary models, based on nonparametric models and parametric linearity tests.
Journal ArticleDOI
Tests of Independence and Randomness Based on the Empirical Copula Process
Christian Genest,Bruno Rémillard +1 more
TL;DR: In this article, it was shown that linear rank statistics have the same asymptotic distribution in both serial and non-serial copula processes, and that the limiting process has the same joint distribution in the serial case as in the non serial case.
Journal ArticleDOI
Kendall's tau for serial dependence
TL;DR: In this paper, the authors show how Kendall's tau can be adapted to test against serial dependence in a univariate time series context and provide formulas for the mean and variance of circular and noncircular versions of this statistic, and prove its asymptotic normality under the hypothesis of independence.
Journal ArticleDOI
Optimal rank-based procedures for time series analysis: testing an arma model against other arma models
Marc Hallin,Madan L. Puri +1 more
TL;DR: In this paper, a distribution-free asymptotically maximin-optimal test statistic was derived for a rank-based, weighted version of the classical Box-Pierce portmanteau statistic.
Journal ArticleDOI
Measures of Dependence and Tests of Independence
TL;DR: In this paper, the authors surveyed measures of dependence and resulting tests of independence and examined measures arising both from linear and nonlinear modeling, and the main emphasis is on some recently developed nonparametric tests using estimated distribution and density functions.