Abstract
An important problem in frequency analysis is the selection of an appropriate probability distribution for a given sample data. This selection is generally based on goodness-of-fit tests. The goodness-of-fit method is an effective means of examining how well a sample data agrees with an assumed probability distribution as its population. However, the goodness of fit test based on empirical distribution functions gives equal weight to differences between empirical and theoretical distribution functions corresponding to all observations. To overcome this drawback, the modified Anderson–Darling test was suggested by Ahmad et al. (1988b). In this study, the critical values of the modified Anderson–Darling test statistics are revised using simulation experiments with extensions of the shape parameters for the GEV and GLO distributions, and a power study is performed to test the performance of the modified Anderson–Darling test. The results of the power study show that the modified Anderson–Darling test is more powerful than traditional tests such as the χ2, Kolmogorov–Smirnov, and Cramer von Mises tests. In addition, to compare the results of these goodness-of-fit tests, the modified Anderson–Darling test is applied to the annual maximum rainfall data in Korea.
Similar content being viewed by others
References
Ahmad MI, Sinclair CD, Werritty A (1988a) Log-logistic flood frequency analysis with historical information. J Hydrol 98:205–224
Ahmad MI, Sinclair CD, Spurr BD (1988b) Assessment of flood frequency models using empirical distribution function statistics. Water Resour Res 24(8):1323–1328
Aho M, Bain LJ, Engelhardt M (1985) Goodness-of-fit tests for the Weibull distribution with unknown parameters and heavy censoring. J Stat Comp Simul 21:213–225
Anderson TW, Darling DA (1952) Asymptotic theory of certain “goodness-of-fit” criteria based on stochastic processes. Ann Math Stat 23:193–212
Arshad M, Rasool MT, Ahmad MI (2003) Anderson Darling and modified Anderson Darling tests for generalized Pareto distribution. Pak J Appl Sci 3(2):85–88
Bush JG, Woodruff BW, Moore AH, Dunne EJ (1983) Modified Cramer von Mises and Anderson-Darling tests for Weibull distributions with unknown location and scale parameters. Comm Stat Theory Meth 12(21):2465–2476
Chandra M, Singpurwalla ND, Stephens MA (1981) Kolmogorov statistics for tests of fit the extreme value and Weibull distributions. J Am Stat Assoc 76(375):729–731
Chowdhury JU, Stedinger JR, Lu LH (1991) Goodness-of-fit tests for regional generalized extreme value flood distributions. Water Resour Res 27(1):1765–1776
Crown JS (2000) Percentage points for directional Anderson–Darling goodness-of-fit tests. Commun Statist-Simula 29(2):523–532
Durbin J (1975) Kolmogorov-Smirnov tests when parameters are estimated with applications to tests of exponentially and test on spacing. Biometrica 62(1):5–22
Fill HD, Stedinger JR (1995) L moment and probability plot correlation coefficient goodness-of-fit tests for the Gumbel distribution and impact of autocorrelation. Water Resour Res 31(1):225–229
Filliben JJ (1975) The probability plot correlation coefficient test for normality. Technometrics 17(1):111–117
Green JR, Hegazy YAS (1976) Powerful modified EDF goodness-of-fit tests. J Am Stat Assoc 71:204–209
Heo J, Kho YW, Shin H, Kim S, Kim T (2008) Regression equations of probability plot correlation coefficient test statistics from several probability distributions. J Hydrol 355(1–4):1–15
Lilliefors HW (1967) On the Kolmogorov–Smirnov test for normality with mean and variance unknown. J Am Stat Assoc 62:399–402
Lilliefors HW (1969) On the Kolmogorov–Smirnov test for the exponential distribution with mean unknown. J Am Stat Assoc 64:387–389
Littell RD, McClave JT, Offen WW (1979) Goodness-of-fit tests for the two parameter Weibull distribution. Comm Stat Simul Comp 8(3):257–269
Looney SW, Gulledge TRJ (1985) Use the correlation coefficient with normal probability plots. Am Stat 39(1):75–79
Murthy PDN, Xie M, Jiang R (2004) Weibull models. Wiley, NJ, USA
Onoz B, Bayazit M (1995) Best-fit distributions of largest available flood samples. J Hydrol 167:195–208
RC NE (1975) Flood studies report, vol 1. Hydrological studies. Whitefraiars Press Ltd, London, UK
Song S, Singh VP (2010) Meta-elliptical copulas for drought frequency analysis of periodic hydrologic data. Stoch Environ Res Risk Assess 24(3):425–444
Stephens MA (1970) Use of the Kolmogorov–Smirnov, Cramer von Mises and related statistics without extensive tables. J R Stat Soc B 32:115–122
Stephens MA (1974) EDF statistics for goodness of fit and some comparisons. J Am Stat Ass 69:730–737
Stephens MA (1976) Asymptotic power of EDF statistics for exponentiality against gamma and Weibull alternatives. Technical report No. 297, Department Statistic Stanford University
Sultan AM, Khaleel HM (2005) A new modified goodness of fit tests for type 2 censored sample from normal population. Math Comput Appl 10(2):165–177
Acknowledgement
This research was supported by a grant (1-6-3) from Sustainable Water Resources Research Center of 21st Century Frontier Research Program.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Shin, H., Jung, Y., Jeong, C. et al. Assessment of modified Anderson–Darling test statistics for the generalized extreme value and generalized logistic distributions. Stoch Environ Res Risk Assess 26, 105–114 (2012). https://doi.org/10.1007/s00477-011-0463-y
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00477-011-0463-y