cancel
Showing results for 
Show  only  | Search instead for 
Did you mean: 
  • New to JMP? Join us Sept. 23-24 for the Early User Edition of Discovery Summit, tailor-made for new users. Register now for free!
  • Use World Cup data to build models, explore spatial relationships, and create informative visualizations in JMP. Register. July 17, 2 pm US Eastern Time.
  • Your voice matters! Tell us how you prefer to receive JMP updates, so we can tailor our communication to your needs. Take short survey.

Discussions

Solve problems, and share tips and tricks with other JMP users.
Choose Language Hide Translation Bar

How to fit a dataset into a theoretical distribution?

I want to fit a dataset into a theoretical distribution to see the best-fit modes. I tried Analyse > Distribution > Continuous Fit > Fit all. I can get the AIC and BIC values, but not the Anderson–Darling values. Essentially, I want to produce a table like the one below. Can anyone help?

Distribution

Anderson–Darling

AICc

BIC

Rank

Lognormal

0.78

552.1

556.8

1

Gamma

1.04

556.9

561.5

2

Weibull

1.32

560.7

565.4

3

Normal

4.51

590.3

594.8

Poor

1 REPLY 1

Re: How to fit a dataset into a theoretical distribution?

What you want is not directly available. It will take some work on your part.

After selecting Fit All, press and hold the Control key on Windows or the Command key on Mac, click the red triangle next to one of the fits (e.g., Fitted Normal Distribution), and select Goodness of Fit. This command will produce the A2 statistic for each fit. Note that this procedure is compute-intensive and might take a couple of minutes to complete. Now right-click on one of the A2 tables and select Make Combined Data Table. That is the second half that you are missing. Go back to the top of the fits, right-click on the table with the AIC values and select Make into Data Table. This is the first half. Now use the Tables > Join command to merge them.

Recommended Articles