Influence Analysis on a Test Statistic in Canonical Correlation Analysis

  • Jung, Kang-Mo (Department of Informatics and Statistics, Kunsan National University)
  • Published : 2001.08.01

Abstract

We propose a method for detecting influential observations that have a large influence on the likelihood ratio test statistic for the two sets of variables are uncorrelated with one another. For this purpose we derive a local influence measure for the likelihood ratio test statistic under certain perturbation scheme. An illustrative example is given to show the effectiveness of the proposed method on the identification of influential observations.

Keywords

References

  1. Journal of the Royal Statistical Society, Series B v.48 Assessment of local influence(with discussion) Cook,R.D.
  2. Residuals and influence in regression Cook,R.D.;Weisberg,S.
  3. Journal of Applied Statistics v.27 Local influence assessment in canonical correlation analysis Jung,K.M.
  4. The Korean Communications in Statistics v.6 Influence analysis of the likelihood ratio test in multivariate Behens-Fisher problem Jung,K.M.;Kim,M.G.
  5. Journal of the American Statistical Association v.83 Regression transformation diagnostics using local influence Lawrance,A.J.
  6. Multiariate analysis Mardia,K.V.;Kent.J.T.;Bibby,J.M.
  7. Psychometrika v.57 Influence in canonical correlation analysis Romanazzi,M.