Friday, 8 November 2013

Online Empirical CDF plotter with Zoom

Please click for additional datasets to plot

Enter number of bins for CDF:-

This blog post contains an online (empirical) Cumulative Density Function (CDF) plotter for multiple data series, where the x-axis is the sample value and the y-axis will be the Empirical CDF normalised to unity. You can specify the number of bins within all the CDFs by filling in the field directly above - the acceptable range is between 10 and 2000 inclusive. Leaving this field blank sets the number of bins to the sample size for each group.

Simply click on the link near the top to add extra text boxes - the first box is filled in with some default values which are plotted in the graph at the bottom, for illustration purposes. Each text box stores a single group/dataset and needs to be filled in with comma separated numbers. Alternatively, you can choose two file entry methods:-

  1. Select multiple single column CSV files to populate the text boxes by repeatedly pressing the Choose File button - there must be one distinct (and differently named) file for each text box i.e. one file per group. Each file can have a different number of samples.
  2. Select a single multi-column CSV file by pressing the Choose File button once, where the number of columns equals the number of groups - all groups need to have the same number of samples.

The graphs at the bottom will display CDFs for all the datasets, once the Plot CDF button is pressed.

You can choose either a line or bar plot, or both, by selecting the appropriate checkboxes below. If neither checkboxes are selected, the plot will default to line and bar plot. Having selected the appropriate checkboxes, you will need to press the Plot Histogram button again.

You can initiate the zoom facility by first pressing the Plot CDF button, then selecting a rectangle in either the shorter ("overview") graph display or in the main graph. To undo the zoom process, simply press the Plot CDF button again.

Below the graphs, summary statistics for all the plotted datasets will be displayed in a table format when the Plot CDF button is pressed. If all samples are greater than zero in value, the Geometric Mean and the Harmonic Mean will be evaluated as well.

The CDF plotter can be used to measure various interquartile ranges.

CDF of all the datasets
Cum. Freq.
Sample value
Cum Freq

Summary statistics pending..

No comments:

Post a Comment