NCL Home > Documentation > Functions > General applied math, Statistics

zscore

Computes the zscore of a variable's given dimensions at all other dimensions and retains metadata.

Available in version 6.5.0 and later.

Prototype

load "$NCARG_ROOT/lib/ncarg/nclscripts/csm/contributed.ncl"  ; This library is automatically loaded
                                                             ; from NCL V6.2.0 onward.
                                                             ; No need for user to explicitly load.

	function zscore (
		x        : numeric,  
		flag [1] : integer,  
		dims [*] : integer   
	)

	return_val  :  float or double

Arguments

x

A variable of numeric type and any dimensionality.

flag

A flag to indicate the sample or population standard deviation.

  • flag=0: use the sample standard deviation: use [N-1] where N is the sample size
  • flag=1: use the population standard deviation: use N, the full sample size

dims

The dimension(s) of x on which to calculate the Z-score.. Must be consecutive and monotonically increasing.

Description

Assuming a normal distribution, a Z-score (aka, standard score) is the number of population standard deviations from the population mean a data point is. But more technically, it's a measure of how many population standard deviations below or above the populatio n mean a raw score is. In practice, the sample mean and sample standard deviation are substituted for the population values.

Examples

Example 1: The following example matches the results at: scipy.stats.zscore


  x  = (/0.7972,  0.0767,  0.4383,  0.7866,  0.8091, \
         0.1954,  0.6307,  0.6599,  0.1065,  0.0508  /)

  z0 = zscore(x, 0, 0)
  z1 = zscore(x, 1, 0)

  print(z0)
  print(z1)
  print(sprintf("%6.4f" ,z0)+"  "+sprintf("%6.4f" ,z1))
The (slightly) edited output is:

     Variable: z0
     Type: float
     Total Size: 40 bytes
                 10 values
     Number of Dimensions: 1
     Dimensions and sizes:   [10]
     Coordinates: 
     Number Of Attributes: 3
       long_name :   Z-Score
       method :      Z=(x-xmean)/xstd ; sample std
       NCL : zscore
     
     Variable: z1
     Type: float
     Total Size: 40 bytes
                 10 values
     Number of Dimensions: 1
     Dimensions and sizes:   [10]
     Coordinates: 
     Number Of Attributes: 4
       long_name :   Z-Score
       method :      Z=(x-xmean)/xstd ; population std
       NCL : zscore

---
                 z0       z1
     (0)      1.0694   1.1272
     (1)     -1.1830  -1.2470
     (2)     -0.0526  -0.0554
     (3)      1.0363   1.0923
     (4)      1.1066   1.1665
     (5)     -0.8119  -0.8558
     (6)      0.5489   0.5786
     (7)      0.6402   0.6748
     (8)     -1.0898  -1.1488
     (9)     -1.2640  -1.3323