Description
Estimating cointegrating relationships requires specific techniques. Canonical correlations are used to determine the rank and space of the cointegrating matrix. The vectors used to transform the data into canonical variables have an eigenvector representation, and the associated canonical correlations have

Estimating cointegrating relationships requires specific techniques. Canonical correlations are used to determine the rank and space of the cointegrating matrix. The vectors used to transform the data into canonical variables have an eigenvector representation, and the associated canonical correlations have an eigenvalue representation. The number of cointegrating relations is chosen based upon a theoretical difference in the convergence rates of the eignevalues. The number of cointegrating relations is consistently estimated using a threshold function which places a lower bound on the eigenvalues associated with cointegrating relations and an upper bound on the eigenvalues on the eigenvalues not associated with cointegrating relations. The proposed estimator performs better with a large number of cross-sectional observations and moderate time series length.
Reuse Permissions
  • Downloads
    pdf (667.9 KB)

    Details

    Title
    • Estimation and hypothesis testing of cointegration
    Contributors
    Date Created
    2012
    Resource Type
  • Text
  • Collections this item is in
    Note
    • Partial requirement for: Ph. D., Arizona State University, 2012
      Note type
      thesis
    • Includes bibliographical references (p. 43-44)
      Note type
      bibliography
    • Field of study: Economics

    Citation and reuse

    Statement of Responsibility

    by Adam Nowak

    Machine-readable links