Subscribe to DSC Newsletter

I am a stats newbie. A geoscientist with only undergrad stats training. Doing “pure” prediction, no clustering. Have generated a predictive algorithm using several different techniques. Best regression coefficient was 0.85 with K-NN. I expected to have to input geospatial data along with the data for the predictors (6) and predicted.

Can K-NN work like this or is it’s algorithm and predictions 100% spurious ?

Thanks. 

Views: 287

Reply to This

Replies to This Discussion

Hi Randolph, you might want to explore kriging, as this is a popular tool for geoscientists. The book from Noel Cressie also addresses this topic and much more in the context of spatial statistics, see here

Thank you again Vincent. I will follow-up. 

Vincent Granville said:

Hi Randolph, you might want to explore kriging, as this is a popular tool for geoscientists. The book from Noel Cressie also addresses this topic and much more in the context of spatial statistics, see here

RSS

Videos

  • Add Videos
  • View All

Follow Us

© 2018   Data Science Central ®   Powered by

Badges  |  Report an Issue  |  Privacy Policy  |  Terms of Service