Wald Tests of I(1) against I(d) Alternatives: Some New Properties and an Extension to Processes with Trending Components

Institut d'Analisi Economica (CSIC)
Studies in Nonlinear Dynamics & Econometrics 02/2008; 12(4):1562-1562.
Source: RePEc

ABSTRACT This paper analyses the behaviour of a Wald-type test, i.e., the (Efficient) Fractional Dickey-Fuller (EFDF) test of I(1) against I(d), d<1, relative to LM tests. Further, it extends the implementation of the EFDF test to the presence of deterministic trending components in the DGP. Tests of these hypotheses are important in many macroeconomic applications where it is crucial to distinguish between permanent and transitory shocks because shocks die out in I(d) processes with d<1. We show how simple the implementation of the EFDF in these situations is and argue that, under fixed alternatives, it is preferred to the LM test in Bahadur's sense. Finally, an empirical application is provided where the EFDF approach allowing for deterministic components is used to test for long-memory in the GDP p.c. of several OECD countries, an issue that has important consequences to discriminate between alternative growth theories.

  • [Show abstract] [Hide abstract]
    ABSTRACT: Lobato and Velasco (20077. Lobato , I. and Velasco , C. 2007 . Efficient wald tests for fractional unit roots . Econometrica , 75 : 575 – 90 . [CrossRef], [Web of Science ®]View all references) introduced a test for a unit root against fractional alternatives with good power and performance properties. The purpose of this article is to examine the size of the test in the presence of level and trend breaks under the null hypothesis. The results suggest that test size remains relatively unaffected by level breaks but that the test can be undersized when there are breaking trends.
    Applied Economics Letters 01/2012; 19(1):83-85. · 0.23 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents an overview of some new results regarding an easily implementable Wald test-statistic (EFDF test) of the null hypotheses that a time-series process is I(1) or I(0) against fractional I(d) alternatives, with d?(0,1), allowing for unknown deterministic components and serial correlation in the error term. Specifically, we argue that the EFDF test has better power properties under fixed alternatives than other available tests for fractional roots, as well as analyze how to implement this test when the deterministic components or the long-memory parameter are subject to structural breaks.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Romero-A´ vila and Usabiaga (2007) find that many U.S. state unemployment rates are stationary, a result at odds with the traditional view that unemployment rates are pathdependent and subject to shocks that have permanent effects. They base their results on multivariate unit root tests that provide for two breaks in mean. This note extends the analysis to directly examine whether the series were fractionally integrated. When no allowance is made for breaking means, the results suggest evidence in favor of hysteresis, an outcome that generally applies when one break in mean is considered. Allowing for two breaks demonstrates that the evidence in favor of the natural rate and the hysteresis hypotheses is temporally sensitive.
    Southern Economic Journal 01/2009; 76(2):458-466. · 0.63 Impact Factor

Full-text (2 Sources)

Available from
May 29, 2014