Statistics Toolbox

Empirical Cumulative Distribution Function (CDF)

If you are not willing to assume that your data follows a specific probability distribution, you can use the cdfplot function to graph an empirical estimate of the cumulative distribution function (cdf). This function computes the proportion of data points less than each x value, and plots the proportion as a function of x. The y-axis scale is linear, not a probability scale for a specific distribution.

This example shows the empirical cumulative distribution function for a Weibull sample.

• y = weibrnd(2,0.5,100,1);
  cdfplot(y)
  
  
  

The plot shows a probability function that rises steeply near x=0 and levels off for larger values. Over 80% of the observations are less than 1, with the remaining values spread over the range [1 5].

Weibull Probability Plots

Scatter Plots