Skip to content

Goodness-Of-Fit test for normality based on elimination of parameters

License

Notifications You must be signed in to change notification settings

turkunov/pem-test

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

13 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

PEM test library

Installation

pip install pemtest

What is PEM test?

When performing data analysis, sometimes people come across a problem of checking null hypothesis for normality without knowing parameters of the distribution. In this case we should use tests like "Parameters Elimination Method". PEM test allows us to get rid of mu and sigma and move from performing a test for normality to performing a test for uniform distribution with parameters 0, 1.

Looks hard. Will there be any further explanation?

Yes. You can read full documentation on the algorithm based on PEM test here.

Are there any examples?

Yes, here's an interactive notebook with examples: https://colab.research.google.com/drive/15SR2hJpejqQ8G-I0SXk-WZMZUpsbUdAC?usp=sharing

Who is the author of this algorithm?

turkunov @ Github (me). The algorithm is based on the research done by Sarkadi K. in "On testing for normality" (1960) [p. 269-275].

About

Goodness-Of-Fit test for normality based on elimination of parameters

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published