1. I have points containing data on temperature from 1951-2000. All data have X,Y coordinates.
  2. I have raster files in the same period.
  3. Two data sets have different data processing hence different values at any given point X,Y

My questions are:

  1. Is there a way through ArcGIS 10.0 where I can conduct correlation at every point x,y (point vs raster)?
  2. Is there a way where I can get the RMSE?
  3. Is there a way where I can generate time-series graphs at X,Y?

closed as too broad by PolyGeo Mar 20 '18 at 3:19

Please edit the question to limit it to a specific problem with enough detail to identify an adequate answer. Avoid asking multiple distinct questions at once. See the How to Ask page for help clarifying this question. If this question can be reworded to fit the rules in the help center, please edit the question.

  • 1
    I think your three questions may be better asked/researched separately as per the "one question per question" of the Tour. – PolyGeo Sep 30 '14 at 4:56
  • As correlation needs to variables you have one from(1) and generate second from the rasters by Extract by points(in Spatial analyst Extension) command in arcgis..Then go to correlation in any platform you want e.g ms excel etc. – SIslam Sep 30 '14 at 5:19

Much like jbsoq.

1) Convert the x,y data to a shapefile, here is the tutorial.

2) "Sample" or "Extract Multi Values to Points" to get the raster into the point shapefile. I prefer multi value.

3) Run Exploratory Regression on the data and his will give you most of what you want.

4) You now have the original values and the raster values in the attribute table. I would export this data to dbf or excel and get the RSME in a stat package. It is simple to do in R (RSME) or r just do the math in the attribute table.


To add to msi_g's answer above: since you have multiple rasters you can use Extract Multi Values to Points then add a field to the attribute table of the point data and calculate whatever you want for all points individually, but you will have to type out the equation yourself. Also be cautious with multiple rasters that projections are the same and rasters are snapped (aligned) if the rasters were generated using different processes. For a graph I'd agree on exporting being the easiest solution.

  • Arc does have some graphing tools, but they are more limited than excel, which is more limited than R – jbosq Oct 3 '14 at 2:26

Not the answer you're looking for? Browse other questions tagged or ask your own question.