EBK Regression Prediction - overlap factor

10-26-2017 07:21 PM
New Contributor III

Are there any resources available which provide further detail on overlap factor?

A factor representing the degree of overlap between local models (also called subsets). Each input point can fall into several subsets, and the overlap factor specifies the average number of subsets that each point will fall into. A high value of the overlap factor makes the output surface smoother, but it also increases processing time. Values must be between 1 and 5. If Subset polygon features are supplied, the value of this parameter will be ignored.

My assumption is that if the value is 1, all input points can only exist in one local model.

If the value is 2, all input points can exist in one or two local models.

Any information on the models justification for allowing an input point to be used in 1 or 2 or more local models would be appreciated.


0 Kudos
2 Replies
MVP Esteemed Contributor

Angus... I would look in-house for guidance



Konstantin Krivoruchko and Linda Beale shouldn't be hard to track down.

New Contributor III

Thank you Dan, I have reached out.

I'll post an answer/summary to this thread as soon as I can.