Spatial Statistics Resources

Whenever we look at a map, we inherently start turning that map into information by finding patterns, assessing trends, or making decisions. Spatial statistics empowers you to answer questions confidently and make important decisions using more than simple visual analysis. Below are resources that will help you learn more. If you have questions or awesome analysis stories, there is now a Spatial Statistics Forum on GeoNet — We’d love to hear from you!

Esri’s Spatial Statistics team is hiring!!  We have 2 open positions: We are looking for a kick-butt developer and someone to help us make our tools bulletproof.  Check out the openings here if you’re interested in joining an awesome team of passionate people building the next generation of spatial analysis tools. 

We’re also looking for an awesome developer to help bring data visualization to new levels throughout the ArcGIS platform, paving the way for new kinds of spatial analysis and data exploration. 


Critical Space Time Pattern Mining Patch 

Unfortunately the initial release of the new Space Time Pattern Mining toolbox contains a substantial logic flaw in the Create Space Time Cube tool which makes the results from the Emerging Hot Spot Analysis tool unreliable.  Regrettably you must rerun all of your previous analyses using the provided fix.

Presentations from the UC
  • Spatial Statistics: Simple Ways to Do More with Your Data (2015 VideoPDF)
  • Spatial Data Mining: A Deep Dive into Cluster Analysis (2014 VideoPDF)
  • Beyond Where: Modeling Spatial Relationships Using Regression Analysis (2014 VideoPDF)
  • Applying Spatial Statistics: The Analysis Process in Action (2015 Video)

Brand new to spatial statistics?
Start here → 
  1. Spatial Statistics: Simple Ways to Do More with Your Data (VideoPDF, 2015 UC slides)
  2. Spatial Data Mining: A Deep Dive into Cluster Analysis (VideoPDF, 2015 UC slides)
  3. Hot Spot Analysis for ArcGIS 10.1 (Tutorial)
  4. Beyond Where: Modeling Spatial Relationships Using Regression Analysis (VideoPDF)
  5. Beyond Where: Using Regression Analysis to Explore Why (Tutorial)

Now that you have the essentials, dive deeper!
Summarize Use descriptive statistics to explore your data
  • Spatial Statistics: Simple Ways to Do More with Your Data (VideoPDF)
  • Spatial Distribution of Piracy (Video)
  • Spatial Pattern Analysis of Dengue Fever (Video)

Find clusters  Discover hot spots, cold spots and outliers 
  • Spatial Data Mining: A Deep Dive into Cluster Analysis (VideoPDF)
  • (New!)  Analyzing violent crime (Tutorial)
  • Hot Spot Analysis Tutorial for ArcGIS 10.1 (Tutorial)
  • Hot Spot Analysis Tutorial for ArcGIS 10.0 (Tutorial)
  • Spatial Pattern Analysis of Dengue Fever (Tutorial)
  • Spatial Statistics ModelBuilder Tutorial for ArcGIS 10 (Tutorial)
  • Hot Spot Analysis Part 1 (Video
  • Hot Spot Analysis Part 2 (Video)
  • Hot Spot Analysis Part 3 (Video)

Model relationships  Explore the question “why?” and make predictions
  • Answering WHY Questions, An Introduction to using regression analysis with spatial data (Article)
  • Beyond Where: Modeling Spatial Relationships Using Regression Analysis (VideoPDF)
  • Regression Analysis Basics (Online Documentation)
  • What they don’t tell you about regression analysis (Online Documentation)
  • Regression Analysis in ArcGIS 10 (Tutorial)
  • Regression Analysis in ArcGIS 9.3/9.3.1 (Tutorial)

Tips and tricks  Pro tips you should know

Putting it all together Walk through a real analysis from start to finish 
  • Applying Spatial Statistics: The Analysis Process in Action (VideoPDF)
  • Spatial Statistics Best Practices:  From Hot Spot Analysis all the way through Regression Analysis (Video)
  • Applying GWR in Real Estate Analysis.  An example from Marquette, Michigan. (Article) 

Articles and blogs 

Model and script tools

Read more  Our suggested book list 
  • Mitchell, Andy. The ESRI Guide to GIS Analysis, Volume 2 ESRI Press, 2005.
  • Fotheringham, Stewart A., Chris Brunsdon, and Martin Charlton. Geographically Weighted Regression: the analysis of spatially varying relationships. John Wiley & Sons, 2002.

Resources last updated July 28th, 2015

This entry was posted in Analysis & Geoprocessing and tagged , , , . Bookmark the permalink.

Leave a Reply


  1. eulessdave says:

    Also, there are two books from ESRI Press on using the Spatial Analysis and Spatial Statistics tool. It’s the same book, but the first is the ArcGIS 9.3 version and the second is the ArcGIS 10 version.

    GIS Tutorial II (9.3) -
    GIS Tutorial 2 (10)-

  2. sperrys says:

    The Geographic Weighted Tool in 10.1 cannot write out a raster coefficient files. Everything else works. Error is the infamous “ERROR 999998: Unexpected Error”. It can’t create output raster. It completes the first coefficient file, but the program crashes about 20% into the second coefficient file and deletes all files. I was able to examine the first file once before it crashed. It did not have any useful data or use use the environment settings. Has anyone made it work?

  3. mtuffly says:

    Dear ESRI I have a question regarding the creation of a spatial weight matrix (SWM). I have a data set that contains 71 points depicting ozone values for two time periods (n = 142). When I create a SWM for each time period separately (i.e. independent of time) and run Moran’s I I get the same results as my R Morans’ I. That is ArcGIS and R produce the same results in Morans’ I; hence both methods must porduce the same SWM. So this is a good check.

    Now here is where things get interesting. When I create a SWM in ArcGIS using the concept of TIME_SPACE and run Morans’I I get different results when compared to my R program using Moran’s I. Since I have concluded that Moran’s I is calculated the same in both my R program and ArcGIS the issue must lies in the generation of the SWM under the concept TIME_SPACE. So my questions is how does ArcGIS combine the matrices generated from the 71 points over two time periods. My SWM generated in R is 142 rows by 142 columns. If I take the ArcGIS SWM convert it to a tables I get 11534 records. If my guess is true (e.g. every table record is a element in the matrix) then ArcGIS does not create a symmetrical matrix. That is the root of 11534 is 107.4

    In simple terms how are the intput matrix for the two time periods combine to create a single SWM.


  4. janikas says:

    It should be symmetric… but… the sum of the non-zero elements of the weights matrix does not have to have an even square in order to be symmetric. It should be even… which it is… but symmetry would need to be verified separately using linear algebra on a full matrix or by using read/neighbor check in Python. I could help you further offline if you want and we can get to the bottom of it… you could elaborate on which functions you are using in R and I could give you some Python code to test the symmetry of a SWM file. You can reach me at

  5. mtuffly says:

    Question about Geographic Weighted Regression (GWR)
    If I have 73 points (n = 73) and I run GWR using these 73 points and the CV method coupled with my covariates (3 in number). I get 73 unique equations with four coefficients. When I use the option to create the surface of the GWR coefficients the GWR tool creates the correct number of surfaces associated with the number of covariates and intercept.

    To be specific what is the decay function used in the output. That is, how are the cell values calculated (decayed) between my observed points.



  6. lynn_carlson says:

    Any update on when the Space-Time Cube Utilities toolbox for use with ArcGIS Pro will be available? I cannot find it anywhere, and above it indicates it would be ready at 10.3 release. If it has been released, can you provide the link?

    • lrosenshein says:

      Hi Lynn,
      These tools will be released when ArcGIS Pro is released. I have updated the post to reflect this, and I will update again as soon as we release the utilities.

  7. yochai7 says:

    I can’t get the spatial stats videos on this site to work? is their a new URL for them?


  8. crossrun21 says:

    When running the exploratory regression script I receive the following error message:
    header = WU.readWeightsHeader(weightsFile)
    AttributeError: ‘module’ object has no attribute ‘readWeightsHeader’
    I cannot determine the cause of this error. Has anyone else run into this error and may have a solution?

  9. nabeelawan says:

    what is the default value for “Distance Increment” in “incremental Spatial Autocorrelation” and in the case of 911 emergency tutorial can we use the “Average Nearest Neighbor tool ” for aggregated layer or collect event to check the average nearest neighbor and then use this value for “Distance Increment”…. high value in the graph can be used for Distance band in hot spot tool. Thanks

  10. sperrys says:

    Does anyone know if there an issue Exploratory Regression? It does not run for me in 10.3.1.