Creating Jenks splits

[Abhilasha Sahay]

Hi

I am trying to create cluster my sample using Jenks natural breaks optimization, which minimizes each class’s average deviation from the class mean, while maximizing each class’s deviation from the means of the other groups.

Is there any command on Stata to perform this?

Thanks!

[Nick Cox]

My understanding of this method is that it's based on sum of squared deviations from possible means as a minimand, not "average deviation", whatever that means.

See group1d from SSC as announced on https://www.stata.com/statalist/arch.../msg00883.html and discussed occasionally since.

https://stats.stackexchange.com/ques...ets-e-g-income includes discussion linking the ideas discussed in the help for that program and the Jenks method.

[Abhilasha Sahay]

Thank you.
I had gone through these links. Perhaps, I wasn't able to understand how group1d helps in creating Jenks distribution. I have more clarity now.