Hi everyone,
I am not sure if I apply the T-Test correctly to my data. In the description it says "H = TTEST(X) performs a t-test of the hypothesis that the data in the vector X come from a distribution with mean zero, and returns the result of the test in H." That is my code:
load stockreturnsx = stocks(:,3);x1=x-mean(x);x2=x+10;[h,p,ci,stats] = ttest(x,0,'Alpha',0.01);[h1,p1,ci1,stats1] = ttest(x1,0,'Alpha',0.01);[h2,p2,ci2,stats2] = ttest(x2,0,'Alpha',0.01);
The way I understand it, the T-Test checks if your data is t-distributed with a mean of 0. If I know that my data has a mean of e.g. 10, the T-Test gives really bad results, because the mean is not 0. If I still want to find out if there is a t-distribution, can I substract 10 from my data and apply the T-Test without making any serious error?
If I substract the mean of my data (line 3) the P value becomes 1 in every case. Why is that?
I assume that when I substract the mean, the criterion of 0 mean is met. But that doesn't necessarily mean that I have a T-distribution, right? So if I substract the mean of my values and p becomes 1, I have a T-distribution?
I'm sorry for my confusing words. I hope you understand what I mean.
Best Answer