Anderson Darling Test P Value. The data is not normal. Note that the result is different from that of the Kolmogorov-Smirnov Test where p-value 043.
Note that p-value 040459 and so we conclude that the data is significantly different from normality. Median are not equal the Anderson Darling Normality Test p-value is less than 005. The test statistic is A -n -frac 1 n sum_ i1 n 2i-1 ln p_ i ln 1 - p_ n-i1 where p_ i Phi x_ i - overline xs.
It is a modification of the Kolmogorov-Smirnov K-S test and gives more weight to the tails than does.
The data points do not fit along the straight black line. 05 alpha we conclude that the two samples come from the sample distribution. Use the corresponding p-value when available to test if the data come from the chosen distribution. The data points do not fit along the straight black line.
