From Eigenvector Research Documentation Wiki
Revision as of 12:35, 20 December 2011 by imported>Jeremy
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to navigation Jump to search


Summarizing statistics for sample data.


summ = summary(x)
text = summary(x, n)


Given a data matrix (x) (numeric or DataSet object) this function calculates the following statistics for each column of x:

  • mean = mean of the sample
  • std = standard deviation of the sample
  • n = number of observations
  • min = minimum value in the sample
  • max = maximum value in the sample
  • p10 = tenth percentile
  • p25 = twenty-fifth percentile (lower quartile)
  • p50 = fiftieth percentile (median)
  • p75 = seventy-fifth percentile (upper quartile)
  • p90 = nintieth percentile
  • skew = skewness
  • kurt = kurtosis

With only one input, the output is a DataSet object with the above statistics as rows of the matrix. If the second input (n) is also supplied, the output is a text table describing all of the statistics for the first n columns of the input data.

If summary is called without requesting a return value, it prints to the command window a summary table containing up to 20 columns (default), or up to number specified by the (n) input parameter.

If input x is a multi-dimensional array, the statistics are calculated for each multi-dimensional column of the array (the result will have the same dimensions on modes 2-k where k = number of modes in x).


  • x = matrix (column vector) in which the sample data is stored.

Optional Inputs

  • n = number of columns to include in a text-formatted description of the summary statistics. Default is to analyze all columns (if output DataSet is requested), or the first 20 columns (if no output is requested.)


  • summ = a DataSet object with rows corresponding to the statistics described above, or (when the input n is supplied) a text table of the statistics.


summ = summary(x);

See Also