The AndersonDarling test is defined as:
The AndersonDarling test is an alternative to the and goodnessoffit tests.
Perform an AndersonDarling test for normality:
What we really want to know is whether the data are close enough to the normal distribution to allow the use of conventional statistical tests. Unfortunately, a normality test does not answer this question. If sample size is not too large and the Pvalue extremely small, we can reject the null hypothesis that the data come from a normally distributed population. But rejecting the null does not tell us anything about the alternative distribution. However, if we cannot reject the null we cannot conclude that the test confirmed the validity of the normality assumption. As always, absence of proof is not proof of absence. So it looks like formal testing of the normality assumption is rather useless.
The subscript values represent the df. The digits are never italicized. The p values are usually rounded up to a value from the set {.05, .01, .005, .001, .0005, .0001, …} (MacKenzie, 2015). Exact p values are reported only when the null hypothesis H_{0} is marginally accepted (p = .051). Since p values always lies in between 0 and 1, a zero before the decimal point is unnecessary.
The AndersonDarling statistic () is defined as
The general procedure consists of defining a test statistic which is some function of the data measuring the distance between the hypothesis and the data, and then calculating the probability of obtaining data which have a still larger value of this test statistic than the value observed, assuming the hypothesis is true.
The AndersonDarling procedure is a general test to compare the fit of an observed cumulative distribution function to an expected cumulative distribution function.
AndersonDarling Test for Normality  BPI Consulting
It can sometimes be difficult to assess whether a continuous outcome follows a normal distribution and, thus, whether a parametric or nonparametric test is appropriate. There are several statistical tests that can be used to assess whether data are likely from a normal distribution. The most popular are the KolmogorovSmirnov test, the AndersonDarling test, and the ShapiroWilk test^{1}. Each test is essentially a goodness of fit test and compares observed data to quantiles of the normal (or other specified) distribution. The null hypothesis for each test is H_{0}: Data follow a normal distribution versus H_{1}: Data do not follow a normal distribution. If the test is statistically significant (e.g., p_{0}: Data follow a normal distribution when in fact the data do not follow a normal distribution. Low power is a major issue when the sample size is small  which unfortunately is often when we wish to employ these tests. The most practical approach to assessing normality involves investigating the distributional form of the outcome in the sample using a histogram and to augment that with data from other studies, if available, that may indicate the likely distribution of the outcome in the population.
They test the null hypothesis H_{0} that a sample of data came from a normally distributed population. Below are the three most reliable tests for checking normality of data (Razali & Wah, 2011).
Anderson–Darling test  Wikipedia

The Anderson Darling test is used here to develop Anderson
AndersonDarling GOF test.

AndersonDarling test for normality with estimated parameters
In general, critical values of the AndersonDarling test statistic depend on the specific distribution being tested.

AndersonDarling pvalue or Critical Value method; ..
The AndersonDarling test implemented in EasyFit uses the same critical values for all distributions.
ANDERSON darling null hypothesis offers ..
The subscript values represent the df. The digits are never italicized. The p values are usually rounded up to a value from the set {.05, .01, .005, .001, .0005, .0001, …} (MacKenzie, 2015). Exact p values are reported only when the null hypothesis H_{0} is marginally accepted (p = .051). Since p values always lies in between 0 and 1, a zero before the decimal point is unnecessary. The F distribution has two df since it tests if two population variances are equal by comparing the ratio of two variances.
25/10/2017 · The AndersonDarling test for ksamples
A table includes the ShapiroWilk, Kolmogorov, Cramervon Mises, and AndersonDarling test statistics,with their corresponding values,as shown in .
normal distribution  AndersonDarling code test  …
Typically, multiple comparisons tests are conducted only when the null hypothesis H_{0} of homogeneity is rejected. Theoretically, the results of almost all multiple comparisons tests are valid even when the global hypothesis test fails find an overall statistically significant difference in group means (Hsu, 1996, pp 177). Only Fisher LSD (least significant difference) test (rarely used nowadays) makes the assumptions that H_{0} of homogeneity is rejected. However, finding statistical significance in a post hoc analysis is rather unlikely when the global test fails to find an overall significance. Below are the three most reliable multiple comparisons tests (Mary, 2011).
Is there any test for a null hypothesis …
The AndersonDarling statistic (A^{2}) is defined as The null and the alternative hypotheses are: The hypothesis regarding the distributional form is rejected at the chosen significance level () if the test statistic, A^{2}, is greater than the critical value obtained from a table.
MATLAB Central  AndersonDarling Test "adtest"  Repost
Numerical methods
The Tests of Normality table in SPSS produces the Kolmogorov–Smirnov test and the Shapiro–Wilk test. But there are many alternative tests of univariate normality: the Lilliefors test, the Pearson's chisquared test, and the Shapiro–Francia test, D'Agostino's Ksquared test, the Anderson–Darling test, the Cramér–von Mises criterion, and the Jarque–Bera test. The ShapiroWilk test and AndersonDarling test have better power for a given significance compared to KolmogorovSmirnov or Lilliefors test  an adaptation of the Kolmogorov–Smirnov test (Razali, Nornadiah, Wah, Yap Bee 2011).