Increasing reliability of the test for outliers whose magnitude is small


SURVEY REVIEW, vol.38, no.298, pp.274-285, 2005 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 38 Issue: 298
  • Publication Date: 2005
  • Doi Number: 10.1179/003962605790586509
  • Journal Name: SURVEY REVIEW
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.274-285
  • Yıldız Technical University Affiliated: Yes


The power and level breakdown points measure the global reliability of a test in robust statistics. However, they cannot give enough information about the reliability of a test if outliers are small. Hence, mean success rate (MSR) of a test for outliers (such as data snooping, tau-test) was introduced. But, the MSRs of tests for outliers are small. To increase the MSRs (of tests for outliers, we propose a new repetitive test procedure where the weights of the randomly chosen m observations are increased to the same large value such as 4. m(max) is the number of all possible outliers. The test procedure is repeated for a given number of times and tested on a linear regression by a simulation. One hundred generated samples with random errors distributed normally were chosen. Random and influential outliers are considered in the tail regions and in the whole region of a sample. These outliers are randomly generated 100 times for each simulated sample. Repeating the new test procedure only 20 times, the MSR of data snooping and also the MSR of tau-test are increased for one outlier lying between 3 sigma and 6 sigma at a rate of 10% and 20% respectively.