The following screenshots are the results that I have generated using Hot Spot Analysis, Anselin Moran’s and Global Moran’s I to investigate the clustering of soils with high clay content in the six sub-AVAs (Chehalem Mountains, Ribbon Ridge, Dundee Hills, Yamhill-Carlton, McMinnville, and Eola-Amity Hills) of the northern Willamette Valley. I have created quite a few data sets, and am in the process of identifying useful methods for further interogation of my data. Along those lines, I need some feedback regarding the interpretation of these results – any comments would be greatly appreciated.
Percent clay Location Map of the entire Willamette Valley AVA
Percent clay of the entire Willamette Valley AVA (including the six sub-AVAs in the northern portion of the Willamette Valley)
Percent Clay detail of the northern Willamette Valley
Hot Spot Analysis (GiZScore) of Percent Clay; detailed
Hot Spot Analysis (GiPValue) of Percent Clay; detailed
Anselin Moran’s (Cluster/Outlier Type) of Percent Clay; detailed
Anselin Moran’s (LMiZScore) of Percent Clay; detailed
Anselin Moran’s (LMiPValue) of Percent Clay; detailed
Global Moran’s I using a fixed distance of 1,000 meters, 5,000 meters, 10,000 meters, and 15,000 meters
Beautiful maps!
Here are some suggestions that may help with interpretation:
1) I believe the first 3 maps are thematic maps… the blue to red (cold to hot) maps are very, very beautiful! To help distinguish them from the Hot Spot maps, however, it might be best to render them with a single graduated color … I can’t quite see, but I think the class breaks are equal interval ? Alternatively you could use a standard deviation rendering scheme… then the switch in color (red to blue or green to orange) is more justifiable I believe.
2) For hot spot analysis you would only map the Z-Scores… for statistically significant z-scores, the higher the z-score the hotter the hot spot. So if you want to create a prettier map, you can create more class breaks (6 rather than 3 red classes, for example)… just please be sure that z-scores between +/- 1.65 are some kind of beige/white/clear color (the color should communicate: don’t look at me, I’m not important) because we can’t compare z-scores that aren’t significant, and consequently applying any kind of graduated color to those values isn’t really valid. Hope that makes sense.
3) The red and blue colors for the hot spot maps are statistically significant spatial clusters of high and low values. z-scores and p-values have a one to one correspondence … that is, given a z-score, you can calculate its corresponding p-value. Unlike z-scores, however, p-values are always positive, and small values are most significant (so p-values should definitely be rendered as one graduated color, rather than red to blue… and the small values should be the bright color with larger values becoming more and more beige-ish).
4) Did you use the default rendering for the Local Moran’s I (cluster and outlier) analysis? I know we used to render the z-scores by default, and I don’t remember when we changed it… but the COType Field is the appropriate field to render. HH features are statistically significant clusters of high values; LL features are statistically significant clusters of low values; HL is a statistically significant outlier where a high value is surrounded by low values; LH is a statistically significant outlier where a low value is surrounded by high values. It is best to render the COType field because large positive z-scores correspond to BOTH hot and cold spots (only the COType says which). Large negative z-scores are the outliers (only the COType says if it is HL or LH).
Hope this helps 🙂
Lauren