Acta mathematica scientia,Series A

• Articles • Previous Articles     Next Articles

Detection of Mutiple-outliers in Random-effects Model of Balanced One-way Classification

Shi Lei; He Liping; Huang Mei   

  1. Statistics and Mathematics College, Yunnan University of Finance and Economics, Kunming 650221
  • Received:2004-12-17 Revised:2006-01-15 Online:2007-06-25 Published:2007-06-25
  • Contact: Shi Lei

Abstract: This paper studies the detection of multiple-outliers in balanced random-effects model of one-way classification. The authors derive the likelihood ratio test under the mean-shift model in random-effects. The distribution of test statistic is given and employed to obtain the test procedure. The authors also study the test of mean-shift outlier model in error variables, and a score test is used to identify the multiple-outliers in the data.

Key words: Random-effects model of one-way classification, Mutiple-outliers, Test, Score statistic

CLC Number: 

  • 62J99
Trendmd