A Note on Michelacci and Zaffaroni, Long Memory, and Time Series of Economic Growth

Silverberg, Gerald and Verspagen, Bart (2000). A Note on Michelacci and Zaffaroni, Long Memory, and Time Series of Economic Growth. UNU-MERIT Research Memoranda. UNU-MERIT.

Document type:
Report

Metadata
Documents
Versions
Statistics
  • Attached Files (Some files may be inaccessible until you login with your UNU Collections credentials)
    Name Description MIMEType Size Downloads
    rm2000-032.pdf PDF application/pdf 84.08KB
  • Sub-type Working paper
    Author Silverberg, Gerald
    Verspagen, Bart
    Title A Note on Michelacci and Zaffaroni, Long Memory, and Time Series of Economic Growth
    Series Title UNU-MERIT Research Memoranda
    Volume/Issue No. 32
    Publication Date 2000
    Publisher UNU-MERIT
    Language eng
    Abstract In a recent paper in The Journal of Monetary Economics, Michelacci and Zaffaroni (2000)estimate long memory parameters for GDP per capita of 16 OECD countries. In this note weargue that these estimations are questionable for the purposes of clarifying the time seriesproperties of these data (presence of unit roots, mean reversion, long memory) because theauthors a) filter out a deterministic linear-in-logs trend instead of first-differencing in logs,and manipulate the data in other highly questionable ways, b) rely on the semiparametricGeweke and Porter-Hudak (GPH) method as modified by Robinson, which is known to behighly biased in small samples. We re-examine these results using Beran's nonparametricFGN estimator and Sowell's exact maximum likelihood ARFIMA estimator. These methodsavoid the small-sample bias and arbitrariness of the cut-off parameters of Robinson's methodand allow us to control for short memory effects, although the parametric ARFIMA estimatorintroduces specification problems of its own. We also look at the influence of the choice ofsub-periods on the results. Finally, we apply Robinson's method to our treatment of the dataand show that MZ's results no longer hold, nor are their cut-off parameter and filteringinsensitivity claims substantiated.
    Copyright Year 2000
    Copyright type All rights reserved
  • Versions
    Version Filter Type
  • Citation counts
    Google Scholar Search Google Scholar
    Access Statistics: 393 Abstract Views, 64 File Downloads  -  Detailed Statistics
    Created: Fri, 13 Dec 2013, 13:01:02 JST