I would like to know if what I want to calulate has probability of presence/absence is valid or not, and the best way to do it.

I have a collection of points, and each point has 5 neighbors. For each point I know the probability of presence as well as for the 5 neighbor points.

              NPoint2              NPoint3




I would like to calculate a weighted presence probability for |POINT|, by taking into account the probability and distance of each NPoint as well as the |POINT| probability


Your question as written is a bit circular: You stated that you already know the probability for |POINT| as well as its five neighbors. In that case, you have defined away your problem.

As a variant, which may be what you meant, is the case where you dont know the probability at |POINT|, only the probabilities at NPoints 1 - 5. In this case, there is a whole field devoted to this, its called spatial interpolation. This is used extensively in environmental engineering, hydrology, and mining. In your case, you are spatially interpolating probability of presence, instead of concentration or density etc.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.