Creating a CDF in Excel

Question

I am trying to use excel to create a CDF. I have tried a few different methods but can't seem to get the plot correct. I have data similar to the below:

Decision      Score
 Yes           5
 Yes           5
 Yes           4
 Yes           4
 Yes           4
 Yes           3
 No           2
 No           2
 No           1

I want to be able to create the CDF so that I can say something like "40% of yeses had a score of at least 4."

Answer 1

I believe you want something called an empirical distribution function (ECDF). This website describes how to create one in Excel.

I have copied the text in case the link stops working. It says:

Let's say you had 50 observations from an experiment. To create the EDF:

Step 1: Enter your data into column A of a spreadsheet. Sort into ascending order (smallest to greatest).

Step 2: In column B, type k/n , where:

k is the numbered observation (this is easy, it's just 1, 2, 3, 4, 5…)

n is the number in your sample. For this example, I have 50 observations, so I entered 1/50.

For this example, my entries are 1/50, 2/50, 3/50, 4/50, 6/50, 7/50, 8/50, 9/50, 10/50, 11/50, etc...

To plot the EDF simply use column A for x-axis data and column B for y-axis data.

In your case it would be something like this:

Decision      Score     EDF
 Yes           3        0.1666667
 Yes           4        0.3333333
 Yes           4        0.5
 Yes           4        0.6666667
 Yes           5        0.8333333
 Yes           5        1.0
 No           2
 No           2
 No           1