The Korean Journal of Applied Statistics (응용통계연구)

The Korean Statistical Society (한국통계학회)
권호 표지

A Generalized Likelihood Ratio Test in Outlier Detection

이상점 탐지를 위한 일반화 우도비 검정

  • Jang Sun Baek (Department of Statistics, Chonnam National University, Kwangju 500-757, Korea)
  • Published : 1994.09.01
Download PDF
⟨ Previous Next ⟩

Abstract

A generalized likelihood ratio test is developed to detect an outlier associated with monitoring nuclear proliferation. While the classical outlier detection methods consider continuous variables only, our approach allows both continuous and discrete variables or a mixture of continuous and discrete variables to be used. In addition, our method is free of the normality assumption, which is the key assumption in most of the classical methods. The proposed test is constructed by applying the bootstrap to a generalized likelihood ratio. We investigate the performance of the test by studying the power with simulations.

본 연구에서는 핵확산 감시와 관련된 이상점 탐지를 위한 일반화 우도비 검정 방법이 개발되었다. 고전적인 이상점 탐지방법들이 연속형 변수만을 고려한 반면, 본 연구에서 제안된 방법은 연속형 변수, 이산형 변수, 혹은 이산형과 연속형이 혼합된 변수들에 모두 적용될 수 있다. 더우기 대부분의 고전적인 방법들에 있어서 주로 이용된 정규분포 가정을 필요로 하지 않는다. 본 연구에서 제안된 방법은 일반화 우도비에 붓스트랩 방법을 적용하여 구성되었다. 모의 실험을 통하여 검정력을 고찰함으로써 제안된 검정방법의 성능을 연구하였다.

Keywords

References

  1. An, Introduction to Multivariate Statistical Analysis Anderson,T.W.
  2. Applied Statistics v.36 A New Graphical Method for Detecting Single and Multiple Outliers in Univariate and Multivariate Data Bacon-Shone,J.;Fung,W.K.
  3. Outliers in Statistical Data Barnett,V.;Lewis,T.
  4. Applied Statistics v.29 Robust Procedures in Multivariate Analysis: Ⅰ, Robust Covariance Estimation Campbell,N.A.
  5. Applied Statistics v.41 Sequential Application of Wilks's Multivariate Outlier Test Caroni,C.;Prescott,P.
  6. Annals of Statistics v.7 Bootstrap Methods: Another Look at the Jackknife Efron,B.
  7. SIAM The Jackknife, the Bootstrap and Other Resampling Plans Efron,B.
  8. Statistical Science v.1 Bootstrap Method for Standard Errors, Confidence Intervals, and Other Measures of Statistical Accuracy Efron,B.;Tibshirani,R.
  9. Journal of the Royal Statistical Society, Series B v.54 Identifying Multiple Outliers in Multivariate Data Hadi,A.S.
  10. Robust Statistics: The Approach Based on Influence Functions Hampel,F.R.;Ronchetti,E.M.;Rousseeuw,P.J.;Stahel,W.A.
  11. Applied Statistics v.36 On Bootstrapping the Likelihood Ratio Test Statistic for the Number of Components in a Normal Mixture McLachlan,G.J.
  12. The Annals of Mathematical Statistics v.22 Multivariate Correlation Models with Mixed Discrete and Continuous Variables Olkin,I.;Tate,R.F.
  13. Mathematical Statistics and Applications v.B Multivariate Estimation with High Breakdown Point Rousseeuw,P.J.;W.Grossmann(eds.);G.Pflug(eds.);I.Vincze(eds.);W.Wertz(eds.)
  14. Journal of the American Statistical Association v.85 Unmasking Multivariate Outliers and Leverage Points (with comments) Rousseeuw,P.J.;van Zomeren,B.C.
  15. Sankhya v.25 Multivariate Statistical Outliers Wilks,S.S.