Hello,

I have a question about the hot spot analysis. I (still) have an island as a study area. So I created a fishnet over the study area and used the Intersect-tool to "cut the edges" to the size of the study area. Then I used the Spatial Join-Tool to see how many point features are in each cell and performed the Hot Spot Analysis. At the edges of the island, I now have cells that are smaller than others. Does this change the result of the Hot Spot Analysis, or does Hot Spot Analysis just calculate within one cell, and the size of the cell does not matter? If I would use the Intersect after performing the Hot Spot Analysis, would I get a right result? Because then, the Hot Spot Analysis was analysing some areas that are not within the study area and where points could not have been located?

My results seem to be right, still I want to know whether there is such thing as an edge effect here (maybe the effect is very small?)

Thanks for your answers,

Mareike

I have a question about the hot spot analysis. I (still) have an island as a study area. So I created a fishnet over the study area and used the Intersect-tool to "cut the edges" to the size of the study area. Then I used the Spatial Join-Tool to see how many point features are in each cell and performed the Hot Spot Analysis. At the edges of the island, I now have cells that are smaller than others. Does this change the result of the Hot Spot Analysis, or does Hot Spot Analysis just calculate within one cell, and the size of the cell does not matter? If I would use the Intersect after performing the Hot Spot Analysis, would I get a right result? Because then, the Hot Spot Analysis was analysing some areas that are not within the study area and where points could not have been located?

My results seem to be right, still I want to know whether there is such thing as an edge effect here (maybe the effect is very small?)

Thanks for your answers,

Mareike

Good questions!

First, I would recommend the following steps:

1) overlay your island with the fishnet grid.

2) do the spatial join

3) remove any grid cells that fall off the island, or where it would be impossible to have points. You remove these becasue the Gi* statistic conceptually compares the local mean to the global mean, then decides if the difference is significant... when you have cells that fall outside the study area (so that lots of cells have zero values), it brings the global mean down ... With a "sea of zeros" in your dataset, you tend to see anything that is non-zero appearing as a hot spot.

4) If you have a good distance (scale of analysis) for the Distance Band or Threshold Distance parameter in mind (based on your knowledge of what you are studying), great!!! If not, then if you are using ArcGIS 10.0 you will find the Incremental Spatial Autocorrelation sample script (www.esriurl.com/spatialstats ... find "Supplementary Spatial Statistics" for the download) helpful. If you don't have ArcGIS 10.0, you can get the same results by running the Spatial Autocorrelation tool for increasing distances and looking for a peak value (I can give you more information about that if you need me to).

5) Run Hot Spot Analysis on your remaining fishnet grid cells, using the distance you discovered in (4).

Next, to answer your questions about the fishnet grid area (how much of the cell falls into the ocean vs how much falls on the island... I think that's what you are asking): for any of the Distance Conceptualizations (Fixed Distance, for example), the Hot Spot Analysis tool "sees" and treats polygons as point centroids. Does this help?

Please let me know if I didn't answer your question and I am happy to try again :)

Lauren

Lauren M Scott, PhD

Esri

Geoprocessing, Spatial Statistics