Evaluating the Anderson-Darling Distribution
By George Marsaglia, John Marsaglia. 2004
185 citations recorded by the source corpus.
Except for n = 1, only the limit as n approaches infinity for the distribution of the Anderson-Darling test for uniformity has been found, and that in so complicated a form that published values for a few percentiles had to be determined by numerical integration, saddlepoint or other approximation methods. We give here our method for evaluating that asymptotic distribution to great accuracy--directly, via series with two-term recursions. We also give, for any particular n, a procedure for evaluating the distribution to the fourth digit, based on empirical CDF's from samples of size 1010 .
Subfields: Artificial Intelligence, Environmental Engineering, Statistical and Nonlinear Physics
View Paper: https://www.semanticscholar.org/paper/9fd6be3053352ef7bc1b39797eebcd4af05f1c94
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
In Environmental Engineering
In Statistical and Nonlinear Physics
Citations in the corpus
- ATSAS 3.0: expanded functionality and new tools for small-angle scattering data analysis (2021, background): “…goodness of fit of the distribution of standardized residuals, i.e. the differences between experimental data and calculated scattering, divided by the propagated error estimates, to the expected standard normal distribution (Anderson & Darling, 1954; Stephens, 1974; Marsaglia & Marsaglia, 2004).”
- Some solutions to the multivariate Behrens–Fisher problem for dissimilarity‐based analyses (2017, methodology): “…a uniform distribution of p-values under a true null hypothesis; hence, we also formally compared the distribution of p-values obtained by each test under each simulation scenario with a uniform distribution, using the Anderson–Darling test (Anderson & Darling 1954; Marsaglia & Marsaglia 2004).”