On 12/18/2016 7:12 PM, si pal wrote:
> This is a repost since I didn't get a reply:
> Just a quick question about null hypothesis using adtest function in the Stats toolbox for Anderson-Darling Test if the sample X is normal.
> [H,pval,adstat,cv] = adtest(X);
> The return value for H=1. Does this mean that my dataset X is normal?
> Its confusing to read about rejecting the null.
> Any tips would be much appreciated.
Here is a quote from the adtest doc, the entire Description section:
"h = adtest(x) returns a test decision for the null hypothesis that the
data in vector x is from a population with a normal distribution, using
the Anderson-Darling test. The alternative hypothesis is that x is not
from a population with a normal distribution. The result h is 1 if the
test rejects the null hypothesis at the 5% significance level, or 0
null hypothesis = X is normally distributed
h=1 if the null hypothesis is rejected
If hypothesis "X is normally distributed" is rejected, X is likely not
Does this help?