charectristics of a data set for Standardizing

#1
Hi,
for standardizing a data set or (x-mean)/variance we are assuming a Gaussian distribution for the data. What should we do to know that this assumption is valid for our data? should we for example draw the QQ-Plot?
Thanks
 

hlsmith

Less is more. Stay pure. Stay poor.
#2
Common approaches are Q-Q plots, testing the residuals (both group combined, mean calculated, each observation - mean = residual) with a normality test (e.g., Shapiro-Wilk), or sometimes central limit theory of large samples (sample > 30).
 

noetsi

Fortran must die
#3
There are also statistics such as Anderson-Darling although they have weak statistical power. The QQ plot is probably your best bet.