Sup-tests for linearity in a general nonlinear AR(1) model

Econometric Theory (Impact Factor: 0.98). 08/2010; 26(04):965-993. DOI: 10.1017/S0266466609990430
Source: RePEc


We consider linearity testing in a general class of nonlinear time series models of order one, involving a nonnegative nuisance parameter that (a) is not identified under the null hypothesis and (b) gives the linear model when equal to zero. This paper studies the asymptotic distribution of the likelihood ratio test and asymptotically equivalent supremum tests. The asymptotic distribution is described as a functional of chi-square processes and is obtained without imposing a positive lower bound for the nuisance parameter. The finite-sample properties of the sup-tests are studied by simulations.

Download full-text


Available from: Lajos Horvath
  • Source
    • "This is one of testing problems when nuisance parameters are not identifiable under the null hypothesis. Inference under similar situations have been studied by Hansen (1996) and Francq et al. (2010). "
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper investigates the identifiability conditions of M-estimation for some nonlinear time series models. We present primitive conditions for the identifiability in smooth transition GARCH, nonlinear Poisson autoregressive, and multiple regime smooth transition AR models. As an unexpected result, the smooth transition GARCH model turns out not to require the familiar common root condition for the identifiability. The method for verification is anticipated to be applicable to other nonlinear models.
    Full-text · Article · Dec 2013
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we consider a general class of vector error correction models which allow for asymmetric and non-linear error correction. We provide asymptotic results for (quasi-)maximum likelihood (QML) based estimators and tests. General hypothesis testing is considered, where testing for linearity is of particular interest as parameters of non-linear components vanish under the null. To solve the latter type of testing, we use the so-called sup tests, which here requires development of new (uniform) weak convergence results. These results are potentially useful in general for analysis of non-stationary non-linear time series models. Thus the paper provides a full asymptotic theory for estimators as well as standard and non-standard test statistics. The derived asymptotic results prove to be new compared to results found elsewhere in the literature due to the impact of the estimated cointegration relations. With respect to testing, this makes implementation of testing involved, and bootstrap versions of the tests are proposed in order to facilitate their usage. The asymptotic results regarding the QML estimators extend results in Kristensen and Rahbek (2010, Journal of Econometrics) where symmetric non-linear error correction are considered. A simulation study shows that the finite sample properties of the bootstrapped tests are satisfactory with good size and power properties for reasonable sample sizes.
    Full-text · Article · Oct 2010 · Econometric Theory
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper we develop testing procedures for the detection of structural changes in nonlinear autoregressive processes. For the detection procedure we model the regression function by a single layer feedforward neural network. We show that CUSUM-type tests based on cumulative sums of estimated residuals, that have been intensively studied for linear regression, can be extended to this case. The limit distribution under the null hypothesis is obtained, which is needed to construct asymptotic tests. For a large class of alternatives it is shown that the tests have asymptotic power one. In this case, we obtain a consistent change-point estimator which is related to the test statistics. Power and size are further investigated in a small simulation study with a partic-ular emphasis on situations where the model is misspecified, i.e. the data is not generated by a neural network but some other regression function. As illustration, an application on the Nile data set as well as S&P log-returns is given.
    Full-text · Article · Apr 2011 · Journal of Time Series Analysis
Show more