Set raster mask for hot spot analysis

[LaurenCarter1]

Hi
I am running a hot spot analysis for clusters of points within Myanmar using model builder. As the country is long and has many coastal and inland borders, I think the lack of data outside the country is affecting the result. I created a raster to mask out areas outside the country so the analysis would only be inside the borders. I set the geoprocessing environments using the mask but it didnt make any difference to the result. Is there a way to set the mask within model builder? Or any other hints?

Cheers
Lauren

[MarkBoucher]

I think the processing extent is a rectangle. If you give it a mask with a non-rectangular feature, it will set processing extent  using the extreme North-South-East-West coordinates of the envelope that contains the feature. When I've gotten results where the processing extent was somehow set smaller than I wanted, the results were always withing a rectangular "envelope" with N-S-E-W limits. I think to eliminate the data outside, you actually have to use the mask to clip the data or extract by mask. Depending on what you are doing, you may still need to deal with results outside of the data that is left over after the clip or extract.

[LaurenCarter1]

Thanks Mark, I suspected as much. I was just hoping there was another way as it definitely affects the results of the analysis. So extract by mask wont be much use as the results are still skewed.

Thanks anyway
Lauren

[curtvprice]

I am running a hot spot analysis for clusters of points within Myanmar using model builder. As the country is long and has many coastal and inland borders, I think the lack of data outside the country is affecting the result.

This is a classic GIS problem of boundaries getting in the way of your analysis. Density, distance, and direction measures may be quite difficult to perform on real data, which rarely comes your way packaged in neat, square boxes. 😞

You may want to consider using the Delaunay-generated distance weights for your analysis instead of the other distance options. From the help - Modeling Spatial Relationships:

Some analysts consider Delaunay triangulation a way to construct natural neighbors for a set of features. This method is a good option when your data includes island polygons (isolated polygons that do not share any boundaries with other polygons) or in cases where there is a very uneven spatial distribution of features. It is not appropriate when you have coincident features, however. Similar to the K nearest neighbors method, Delaunay triangulation ensures every feature has at least one neighbor but uses the distribution of the data itself to determine how many neighbors each feature gets.