Abstract
Statistical models are often based on normal distributions and procedures for testing this distributional assumption are needed. Many goodness-of-fit tests suffer from the presence of outliers, in the sense that they may reject the null hypothesis even in the case of a single extreme observation. We show a possible extension of the Shapiro-Wilk test that is not affected by such a problem. The presented method is inspired by the forward search (FS), a new, recently proposed, diagnostic tool. An application to univariate observations shows how the procedure is able to capture the structure of the data, even in the presence of outliers. Other properties are also investigated.
Similar content being viewed by others
References
Aitken AC (1935) On least squares and linear combination of observations. J R Statist Soc 55:42–48
Atkinson AC, Riani M (2000a) Robust diagnostic data analysis: transformations in regression. Technometrics 384–397
Atkinson AC, Riani M (2000b) Robust diagnostics regression analysis. Springer, New York
Atkinson AC, Riani M (2001) Regression diagnostics for binomial data from the forward search, The Statistician 63–78
Atkinson AC, Riani M (2002a) Forward search added-variable t-tests and the effect of masked outliers on model selection. Biometrika 89(4):939–946
Atkinson AC, Riani M (2002b) Tests in the fan plot for robust, diagnostic transformations in regression. Chemometrics Intell Laboratory Systems 60:87–100
Atkinson AC, Riani M (2004) The forward search and data visualization, Computat. Statist. 19:29–54
Atkinson AC, Riani M, Cerioli A (2004) Exploring multivariate data with the forward search. Springer, New York
Cohen C, Balakrishnan N (1991) Order statistics and Inference. Academic, New York
D’Agostino R, Stephens M (1986) Goodness-of-fit techniques. Marcel Dekker, New York
Lloyd EH (1952) Least squares estimation of location and scale parameters using order statistics. Biometrika. 39:88–95
Pearson ES, D’Agostino RB, Bowman KO (1977) Tests for departure from normality. Comparison of powers. Biometrika. 64:231–246
Rousseeuw PJ (1984) Least median of squares regression. J. Am. Statist Assoc 79:871–880
Rousseeuw PJ, Leroy AM (1987) Robust regression and outlier detection. Wiley, New York
Royston JP (1982) An extension of shapiro-wilk’s w test of non-normality to large samples. Appl. Statist. 31:115–124
Shapiro SS, Wilk MB, Chen HJ (1968) A comparative study on various test for normality. J. Am. Statistical Associ 63:1343–1372
Shapiro SS, Wilk MB (1965) An analysis of variance test for normality (complete samples). Biometrika 52:591–611
Thode HC (2002) Testing for normality. Marcel Dekker, New York
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Coin, D. Testing normality in the presence of outliers. Stat. Meth. & Appl. 17, 3–12 (2008). https://doi.org/10.1007/s10260-007-0046-8
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10260-007-0046-8