Abstract
Inliers are values hidden in the interior of a sample, which seem to be generated by a different mechanism than the rest of the sample. In the univariate case, it is not unlikely that a single value is extremely close to the mean. Still, a number of values very close to the mean might be suspicious. We look for inlier-contaminated samples because they could hint to data fraud or structural defects. We suppose a method to identify normally distributed inliers in an otherwise normally distributed sample using a likelihood ratio test. The method outperforms a simple Shapiro–Wilk Test on normality.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Chen, H., Chen, J.: The likelihood ratio test for homogeneity in finite mixture models. Can. J. Stat. 29(2), 201–215 (2001)
Chen, J., Li, P.: Hypothesis test for normal mixture models: the EM approach. Ann. Stat. 37(5A), 2523–2542 (2009)
Crainiceanu, C.M., Ruppert, D.: Likelihood ratio tests in linear mixed models with one variance component. J. R. Stat. Soc. Ser. B (Stat. Methodol.) 66(1), 165–185
Di, C., Liang, K.-Y.: On likelihood ratio tests when a nuisance parameter is present only under the alternative. The Johns Hopkins University (2009)
Evans, S.: Statistical aspects of the detection of fraud. In: Lock, S., Wells, F., Farthing, M. (eds.) Fraud and Misconduct in Medical Research. BMJ Publishing Group (2003)
Greenacre, M.J., Öztas Ayhan, H.: Identifying inliers. Working papers 763. Barcelona Graduate School of Economics, September 2015
Muralidharan, K.: Inlier prone models: a review. ProbStat Forum 3, 38–51 (2010)
Naim, I., Gildea, D.: Convergence of the EM algorithm for Gaussian mixtures with unbalanced mixing coefficients. arXiv:1206.6427 (2012)
Pinheiro, J., Bates, D.: Theory and Computational Methods for Linear Mixed-Effects Models, pp. 57–96. Springer, New York (2000)
R Core Team: R: a language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria (2018)
Self, S.G., Liang, K.-Y.: Asymptotic properties of maximum likelihood estimators and likelihood ratio tests under nonstandard conditions. J. Am. Stat. Assoc. 82(398), 605–610 (1987)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Falkenhagen, U., Kössler, W., Lenz, HJ. (2019). A Likelihood Ratio Test for Inlier Detection. In: Steland, A., Rafajłowicz, E., Okhrin, O. (eds) Stochastic Models, Statistics and Their Applications. SMSA 2019. Springer Proceedings in Mathematics & Statistics, vol 294. Springer, Cham. https://doi.org/10.1007/978-3-030-28665-1_26
Download citation
DOI: https://doi.org/10.1007/978-3-030-28665-1_26
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-28664-4
Online ISBN: 978-3-030-28665-1
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)