Remark on stably updating mean and standard deviation of data

  • Authors:
  • Ira W. Cotton

  • Affiliations:
  • National Bureau of Standards, Washington, DC

  • Venue:
  • Communications of the ACM
  • Year:
  • 1975

Quantified Score

Hi-index 48.26

Visualization

Abstract

Although not published as a numbered algorithm, Hanson's article “Stably Updating Mean and Standard Deviation of Data” in the January, 1975, issue of Communications, [1] describes an algorithm for sequentially recomputing the mean and standard deviation of a weighted series of numbers when new numbers are added to the series. The procedure requires that only a summary matrix of data be retained, not the entire series, for the new mean and standard deviation to be computed.