Approximating the Shapiro-Wilk W-test for non-normality Authors
Received: 15 October 1991 Accepted: 15 October 1991 DOI:
Cite this article as: Royston, P. Stat Comput (1992) 2: 117. doi:10.1007/BF01891203 Abstract
A new approximation for the coefficients required to calculate the Shapiro-Wilk
W-test is derived. It is easy to calculate and applies for any sample size greater than 3. A normalizing transformation for the W statistic is given, enabling its P-value to be computed simply. The distribution of the new approximation to W agrees well with published critical points which use exact coefficients. Keywords Non-normality Shapiro-Wilk W-test Download to read the full article text References
Davies, C. S. and Stephens, M. A. (1978) Algorithm AS128. Approximating the covariance matrix of normal order statistics.
Applied Statistics, 27, 206–212.
Royston, J. P. (1982a) An extension of Shapiro and Wilk's
W test for normality to large samples. Applied Statistics, 31, 115–124.
Royston, J. P. (1982b) Algorithm AS177. Expected normal order statistics (exact and approximate).
Applied Statistics, 31, 161–165.
Royston, J. P. (1983) Some techniques for assessing multivariate normality based on the Shapiro-Wilk
W. Applied Statistics, 32, 121–133.
Royston, P. (1991a) Estimation, reference ranges and goodness-of-fit for the three-parameter lognormal distribution.
Statistics in Medicine, in press.
Royston, P. (1991b) Aspects of goodness-of-fit tests for normality. I. Use of the tests when the data contain ties.
Shapiro, S. S. and Francia, R. S. (1972) An approximate analysis of variance test for normality.
Journal of the American Statistical Association, 67, 215–216.
Shapiro, S. S. and Wilk, M. B. (1965) An analysis of variance test for normality (complete samples).
Biometrika, 52, 591–611.
Shea, B. L. and Scallan, A. J. (1988) AS R72. A remark on Algorithm AS128: approximating the covariance matrix of normal order statistics.
Applied Statistics, 37, 151–155.
Verrill, S. and Johnson, A. (1988) Tables and large-sample distribution theory for censored-data correlation statistics for testing normality.
Journal of the American Statistical Association, 83, 1192–1197.
Weisberg, S. and Bingham, C. (1975) An approximate analysis of variance test for non-normality suitable for machine calculation.
Technometrics, 17, 133–134.