ZSCORE removes the mean and normalizes data 
 to a variance of 1. Can be used for pre-whitening of data, too. 

 [z,mu, sigma] = zscore(x [,OPT [, DIM])
   z   z-score of x along dimension DIM
   sigma is the inverse of the standard deviation
   mu   is the mean of x

 The data x can be reconstucted with 
     x = z*diag(sigma) + repmat(m, size(z)./size(m))  
     z = x*diag(1./sigma) - repmat(m.*v, size(z)./size(m))  

 OPT   option 
	0:  normalizes with N-1 [default] when computing sigma
		provides the square root of best unbiased estimator of the variance [1]
	1:  normalizes with N, when computing sigma
		this provides the square root of the second moment around the mean
 	otherwise: 
               best unbiased estimator of the standard deviation (see [1])      

 DIM	dimension
	1: STATS of columns
	2: STATS of rows
	default or []: first DIMENSION, with more than 1 element

 see also: SUMSKIPNAN, MEAN, STD, DETREND

 REFERENCE(S):
 [1] http://mathworld.wolfram.com/z-Score.html

Package: nan