Abstract
For testingk upper or lower outliers in a normal sample, the sampling distribution of the likelihood-ratio statistic is still unknown in the literature except fork=1. In this paper, we find its exact distribution fork=2 and tabulate the extensive critical values, which are compared with the traditional simulated values.
Similar content being viewed by others
References
Barnett, V. andLewis, T. (1994).Outliers in Statistical Data. John Wiley & Sons Chichester, 3rd ed.
Fisher, R. A. (1929). Tests of significance in harmonic analysis.Proceedings of the Royal Statistical Society, 125:54–59.
Grubbs, F. E. (1950). Sample criteria for testing outlying observations.The Annals of Mathematical Statistics, 21:27–58.
Grubbs, F. E. (1969). Procedures for detecting outlying observations in samples.Technometrics, 11:1–21.
Grubbs, F. E. andBeck, G. (1972). Extension of sample sizes and percentage points for significance tests of outlying observations.Technometrics, 14:847–856.
Kimber, A. C. andStevens, H. J. (1981). The null distribution of a test for two upper outliers in an exponential sample.Applied Statistics, 30:153–157.
Zhang, J. (1998). Tests for multiple upper or lower outliers in an exponential sample.Journal of Applied Statistics, 25:245–255.
Zhang, J. andWang, X. (1998). Unmasking test for multiple upper or lower outliers in normal samples.Journal of Applied Statistics, 25:257–261.
Author information
Authors and Affiliations
Corresponding author
Additional information
The research is partially supported by the National Sciences and Engineering Research Council of Canada.
Rights and permissions
About this article
Cite this article
Zhang, J., Yu, K. The null distribution of the likelihood-ratio test for one or two outliers in a normal sample. TEST 15, 141–150 (2006). https://doi.org/10.1007/BF02595422
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/BF02595422