Latest Contributions by EricKrause

Universal kriging is available in the Geostatistical Wizard.  It's one of the six kriging types.  The trend is calculated from polynomials of the (x,y) coordinates; it does not support covariates other than the spatial location.  However, covariates can be used as cokriging variables. ... View more

You may just need to enable the extension.  In ArcMap, go to Customize pulldown menu and select Extensions.  Make sure Geostatistical Analyst is checked.  If that isn't the problem, you'll need to contact Esri support. ... View more

Yes, EBK will work with data with zeroes and negative values.  If you need to use a transformation in EBK, you'll have to use Empirical because Log-Empirical won't work with zeroes. ... View more

You're correct; it is the zeros that are causing the options to be filtered.  We normally have Logarithm, Box-Cox, and Arcsin, but all three methods are not defined for negative values or zeros. If you are looking at transformations in preparation for kriging, we support Normal Score Transformations with simple kriging, and several of these transformations are applicable for negative/zero data values.  Normal score transformations are performed within the Geostatistical Wizard. EDIT:  I misspoke.  Arcsin is defined for data between 0 and 1 (inclusive).  So it can work with zero values, but if any data values are negative or greater than 1, the option will be filtered.  Because the option is filtered for you, you must have some data values larger than 1. ... View more

Trend removal options are not built into Areal Interpolation, but there are a few things you might try. First, you may be able to remove some trend by correcting for anisotropy.  It's one of the options on the covariance curve screen of the Wizard. If that doesn't work, there is a second method that may work, but it is more statistically questionable.  You may be able to represent the polygons as points and use Global or Local Polynomial interpolation to get a general trend.  You can then subtract off this trend from your polygonal data and use areal interpolation on the new detrended data.  After the interpolation, you can add back the trend that you removed.  This methodology is hard to justify if you're using Rate (Binomial) or Event (Overdispersed Poisson) areal interpolation, but it can be reasonably justified for Average (Gaussian). ... View more

GWR does accept binary short integer weight fields. ... View more

Any of the three can be justified, but I prefer fixed distance band among those three.  This is because fixed distance band is the conceptualization where it is most clear that the test statistic will converge to a normal distribution with increasing sample size. If you're getting the results you want/expect from fixed distance band, I would stick with that. ... View more

There are several reasons that a kriging surface can have holes like that.  The most likely reason is that the searching neighborhood is too small. Regardless, we recommend using empirical Bayesian kriging (EBK).  It almost always gives more accurate predictions than traditional kriging. ... View more

We currently do not support true space-time kriging.  You can perform kriging on each time slice independently, but you can't use temporal correlation directly in the kriging model. ... View more

Whether kriging will work really depends on your data and the question you're trying to answer.  We generally use environmental data in examples because this kind of data most often meets the kriging assumptions, but there is really no restriction on the source of the data.  If the data meets the kriging assumptions and it makes sense to interpolate, kriging should work. ... View more

I'm not familiar with the Spatial Statistics tutorial.  You'll probably have more luck on the Spatial Statistics Forum. ... View more

There's a typo in that pdf that I just noticed.  For average standard error, the formula is missing a square.  You can find the correct formulas here: http://resources.arcgis.com/en/help/main/10.1/index.html#//00300000000z000000 "Average Standard Error" is the only formula that is different than you might expect.  It might be better called "Root-Mean-Variance."  We used this formula instead of a simple average because this formula is more directly comparable to the RMS. ... View more

http://dusk.geo.orst.edu/gis/geostat_analyst.pdf The formulas for the crossvalidation summary statistics can be found in Appendix A on page 273 (page 279 of the pdf, since the first six pages aren't numbered). ... View more