Coefficient of Variation

A measure of the volatility or spread of a time series around the average, for example of customer orders, aka Demand Linearity, Process Linearity. Coefficient of Variation (Cv) is the ratio of standard deviation and mean. Cv is useful in comparing the degree of variation between different time series even when the means are different. The higher the Cv the greater the relative variation or spread.

  1. Calculate the standard deviation (s, or σ) of the series … in Excel =STDEV.P(cell range).
  2. Calculate the mean (x, or µ) (or average) … in Excel =AVERAGE(cell range).
  3. Then calculate the ratio of standard deviation and mean.

For customer demand, low variability is typically considered a Cv less then 1.0, very stable demand is a Cv less than 0.

Note that you might want to to discard abnormal demand, and be certain to replace blanks with zeros. Select your time buckets (daily, weekly, monthly) carefully. Daily and weekly data will typically have a ‘noisier’ coefficient of variation than monthly. Monthly buckets won’t be appropriate for dynamic and short leadtime businesses.

Examples …

 

Leave a Comment ...