topic Re: Negative values after areal interpolation in ArcGIS GeoStatistical Analyst Questions

Negative values after areal interpolation

ShuoLiu — Wed, 24 Apr 2013 15:51:46 GMT

Hi, guys.
I have a problems using Areal Interpolation in ArcGIS 10.1.
There's no negative value in my origin data.
And there's no negative in my predicted surface.
But after I used Areal Interpolation layer to to Polygons,there are 75 polygons with a negative value, which they really shouldn't be.
Any ideas why this happened?

Re: Negative values after areal interpolation

EricKrause — Wed, 24 Apr 2013 20:30:29 GMT

Areal Interpolation will often predict outside of the data range. This means that sometimes you can get negative predictions for a phenomenon that can't be negative. Unfortunately, there isn't much you can do to prevent this.

Does your data represent counts? If it does, you should use Event (overdispersed Poisson) areal interpolation. This type of areal interpolation will never predict negative values.

Re: Negative values after areal interpolation

JoshObrecht — Thu, 31 Oct 2013 12:33:57 GMT

What if we don't have count data? Is there a way to not get negative numbers?

Re: Negative values after areal interpolation

EricKrause — Thu, 31 Oct 2013 18:39:11 GMT

We have special models for count and proportion data, but if your data is a continuous variable (like average temperature or median age), you may end up with negative predictions.

You may be able to change the semivariogram parameters to get only positive predictions, but it's difficult to say exactly what you should change because everything is so data-dependent.

Re: Negative values after areal interpolation

ttgrdias — Tue, 03 May 2022 09:25:42 GMT

Hi!

@EricKrauseis there any way to avoid negative prediction values using EBK3D?

Tks,

Re: Negative values after areal interpolation

EricKrause — Tue, 03 May 2022 13:04:28 GMT

@ttgrdias If all of the input data values are positive (no negatives or zeros), then the Log Empirical transformation ensures all predictions will be positive.

Re: Negative values after areal interpolation

ttgrdias — Tue, 03 May 2022 19:22:04 GMT

@EricKrause Ok, thanks. But that doesn't allow to introduce measurement errors, correct?