Troubles with Lillietest and chi2gof

Hi

I generate 100 numbers which came from a normal distribution, and when I use lillietest I get the answer h=0 but when I use the chi2gof test I get the answer h=1.

here is my codes:

A=randn(1,100);
chi2gof(A,'cdf',@(z)normcdf(z,mean(A),std(A)),'nparams',2)
ans =
1

lillietest(A)
ans =
0

can someone please explain why it is like this?

Tanx

[Merged information from other question]

Hello,

I have a problem with hypothesis tests in MATLAB. I have a dataset and I want to know what is the distribution of this dataset. At the first try I used Lillietest which can show me if my data is coming from a normal distribution family or not. At second try I used chi2gof test. Here is the problem, the data which lillietest find it normally distributed, chi2gof test finds it not normally distributed. I want to know what is the difference between this two tests.

Answer 1

[Wayne King]

I don't get that Sasi:

rng default; % let's make sure we're using the same vector
x = randn(100,1);
[h,p] = chi2gof(x,'cdf',{@normcdf,mean(x),std(x)});

Note that the above is the same as:

    [h,p] = chi2gof(x);
    hL = lillietest(x);

[Sasi]

So you mean the answer of [h,p]=chi2gof(x); and [h,p]=lillietest(x)should be the same?

[Wayne King]

You cannot guarantee that they will always be the same.