Talk:Inverse distance weighting

Merge to Inverse distance weighting
If I'm not mistaken, Shepard's method is a subset of the inverse distance weighting methods?+mwtoews 05:14, 21 January 2007 (UTC)
 * Support. --Berland 18:09, 21 June 2007 (UTC)

Value of the denominator exponent
Not an expert by any means, by I would like to see a reference to support the use of d-2 as the "most common" smoothing parameter. From my own experiments, the proper value to use is a function of the density of samples, the degree of smoothing desired and the size of the weighting kernels. So I will edit to match.131.243.35.178 (talk) 01:24, 17 April 2009 (UTC)snuz2

Lizka
I pulled the section. The appropriate bit of the paper is "The proposed weighting coefficients (w = l/(p^3)) for each equation were inversely related to the distance of the corresponding node from the point P and also to the error due to truncating the Taylor series (2)." Needs a much more careful reading however, as this is not all he appears to be doing. User A1 (talk) 11:55, 1 April 2010 (UTC)

Exponent vs. Sharpness
Shouldn't it be the other way around? Exponents >1 (or <-1, if the norm is in the denominator) create less sharp spikes around data points. This is confirmed by the image in the article too. --163.1.81.71 (talk) 14:31, 7 May 2012 (UTC)Student of Bayesian approximation methods
 * You are right. Page updated. Han-Kwang (t) 20:14, 7 May 2012 (UTC)

p value and suggestion
I'm not an expert on weight metrics or this topic, and I feel like this article would benefit if the power 'p' was explained better. Where do we find information on how to determine appropriate or standard values? Second, it would be ideal if there was an example that showed the shepards method being applied to estimate the value of a unknown point from three nearby points. This would help people quickly understand whether or not the methods explained on this page are what they are looking for without having to wade into the equations and read trivia about the historical origin.

esri reference
The cited link to esri has more to do with plugging commercial product than adding to the discussion on inverse distance weighting. The link to Ref 2 is no longer valid.