TOPICS
Search

Anderson-Darling Test


The Anderson-Darling test is a statistical test of whether a sample comes from a specified statistical distribution. It uses the Anderson-Darling statistic, which gives greater weight to discrepancies in the tail probabilities than the Kolmogorov-Smirnov test. Large values of the statistic provide evidence against the hypothesized distribution, with critical values depending on the distribution and on whether its parameters were estimated from the data.


See also

Anderson-Darling Statistic, Kolmogorov-Smirnov Test, Statistical Test, Tail Probability

Explore with Wolfram|Alpha

References

Anderson, T. W. and Darling, D. A. "Asymptotic Theory of Certain 'Goodness of Fit' Criteria Based on Stochastic Processes." Ann. Math. Stat. 23, 193-212, 1952. https://doi.org/10.1214/aoms/1177729437.

Cite this as:

Weisstein, Eric W. "Anderson-Darling Test." From MathWorld--A Wolfram Resource. https://mathworld.wolfram.com/Anderson-DarlingTest.html

Subject classifications