Advertisement

Testing Outliers in Multivariate Data

  • M. L. Tiku
  • M. Singh
Part of the NATO Advanced study Institutes Series book series (ASIC, volume 79)

Summary

Given n random observations on a p-dimensional random vector x, the problem is to test whether a specified number (usually~small) of suspected observations are outliers (too discordant as compared to the bulk of observations). As a generalization of Tiku’s (1975, 1977) univariate statistic, we propose a statistic g for testing a specified number of outliers in multivariate data; g is the ratio of the product of robust estimators (Tiku, 1980) to the product of ordinary estimators of the scale parameters. For the multivariate normal, g is shown to be considerably more powerful than the prominent statistic R (restricted to the multivariate normal) due to Wilks (1963) under location shifts (model A; Barnett and Lewis, 1978) although slightly less powerful under scale changes (model B; Barnett and Lewis). Like R, g is not sensitive to changes in correlations (orientation). The statistic g can be used (under models A or B) for testing outliers in samples from any multivariate distribution whose marginal distributions are of the type (l/σ)f((x-μ)/σ).

Key Words

Multivariate outliers censored samples robust estimators modified maximum likelihood estimators 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Barnett, V. (1978). The study of outliers: purpose and model. Applied Statistics, 27, 242–250.CrossRefGoogle Scholar
  2. Barnett, V. (1979). Some outlier tests for multivariate samples. South African Statistical Journal, 13, 29–52Google Scholar
  3. Barnett, V., Lewis, T. (1978). Outliers in Statistical Data. Wiley, New York.zbMATHGoogle Scholar
  4. Cox, D.R. (1968). Notes on some aspects of regression analysis. Journal of the Royal Statistical Society, Series A, 131, 265–279.CrossRefGoogle Scholar
  5. David, H.A., Paulson, A.S. (1965). The performance of several tests for outliers. Biometrika, 52, 429–436.MathSciNetzbMATHGoogle Scholar
  6. Gnanadesikan, R., Kettenring, J.R. (1972). Robust estimates, residuals, and outlier detection with multiresponse data. Biometrics, 28, 81–124.CrossRefGoogle Scholar
  7. Hawkins, D.M. (1977). Comment on “A new statistic for testing suspected outliers”. Communications in Statistics, A6, 435–438.MathSciNetCrossRefGoogle Scholar
  8. Healy, M.J.R. (1968). Multivariate normal plotting. Applied Statistics, 17, 157–161.MathSciNetCrossRefGoogle Scholar
  9. Johnson, N.L., Nixon, E., Amos, D.E., Pearson, E.S. (1963). Table of percentage points of Pearson curves. Biometrika, 50, 459–498.MathSciNetzbMATHGoogle Scholar
  10. Johnson, N.L., Kotz, S. (1972). Distributions in Statistics: Continuous Multivariate Distributions. Wiley, New York.zbMATHGoogle Scholar
  11. Siotani, M. (1959). The extreme value of the generalized distances of the individual points in the multivariate normal sample. Annals of the Institute of Statistical Mathematics, 10, 183–208.MathSciNetzbMATHCrossRefGoogle Scholar
  12. Tietjen, G.L., Moore, R.H. (1972). Some Grubbs-type statistics for the detection of several outliers. Technometrics, 14, 583–597.CrossRefGoogle Scholar
  13. Tiku, M.L. (1967). Estimating the mean and standard deviation from censored normal samples. Biometrika, 54, 155–165.MathSciNetGoogle Scholar
  14. Tiku, M.L. (1970). Monte Carlo study of some simple estimators in censored normal samples. Biometrika, 57, 207–210.MathSciNetzbMATHCrossRefGoogle Scholar
  15. Tiku, M.L. (1975). A new statistic for testing suspected outliers. Communications in Statistics, 4, 737–752.MathSciNetCrossRefGoogle Scholar
  16. Tiku, M.L. (1977). Rejoinder: “Comment on ‘A new statistic for testing suspected outliers’”. Communications in Statistics, A6, 1417–1422.CrossRefGoogle Scholar
  17. Tiku, M.L. (1978). Linear regression model with censored observations. Communications in Statistics, A7, 1219–1232.MathSciNetCrossRefGoogle Scholar
  18. Tiku, M.L. Singh, M. (1980). Robustness of MML estimators based on censored samples and robust test statistics. Journal of Statistical Planning and Interference, 4, (123–143).zbMATHCrossRefGoogle Scholar
  19. Tiku, M.L. Singh, M. (1980). Robust estimation of the variance-covariance matrix and its use in testing an assumed multivariate distribution, (submitted to JSPI for publication).Google Scholar
  20. Wilks, S.S. (1963). Multivariate statistical outliers. Sankhya, Series A, 25, 407–426.MathSciNetzbMATHGoogle Scholar

Copyright information

© D. Reidel Publishing Company 1981

Authors and Affiliations

  • M. L. Tiku
    • 1
  • M. Singh
    • 1
  1. 1.Department of Mathematical SciencesMcMaster UniversityHamiltonCanada

Personalised recommendations