I have a number of test data (400 samples) that are distributed according to the Gaussian distribution, N(0,sigma). Is there a simple way of calculating the sample standard deviation sigma for these in Matlab? I have used the std function but I'm not sure whether it's correct, since I cannot see any assumptions on distribution in the matlab help except that it's identical.
[Math] Standard deviation for Gaussian distribution in Matlab
MATLABstatistics
Best Answer
The
std
command in Matlab does not assume uniformly distributed samples. The commandstd(x)
is simply calculating the quantity $$ \hat{\sigma}=\sqrt{\frac{1}{n-1}\sum_{i=1}^n(x_i-\bar{x})^2} $$ with $\bar{x}=\sum\limits_{i=1}^nx_i$ for a vectorx
of length $n$. You can easily calculate this quantity by hand and compare with thestd
command.