lrosenshein
Recent Posts
Taking Analysis to the Next Level: Part 1
By Lauren Rosenshein
The Business Analyst team invited me to blog about some work I’ve been doing with the BAO API, and I’m really excited about the opportunity!
As a product engineer on the Geoprocessing and Analysis team, my team and I work hard to push the limits of what spatial analysis is and how it can be used to solve real-world problems, and we often use Business Analyst to take our analysis to the next level.
One very powerful use of spatial analysis and geoprocessing is Continue reading
Spatial Pattern Analysis Free Training Seminar Now Available!
Are you an epidemiologist, crime analyst, demographer, emergency response
planner, transportation analyst, archeologist, wildlife biologist,
retail analyst, or other GIS practitioner interested in moving beyond
putting points on a map to analyzing spatial patterns and trends?
We’re really excited because the recording of the free live training seminar on Spatial Pattern Analysis is now available from the training website: Spatial Pattern Analysis. We had over 2,000 attendees when it aired live, and we’re hoping that even more people are going to be able to take advantage of the recorded version of the seminar. The session talks about:
- Using descriptive spatial statistics to summarize the most
important characteristics of a spatial distribution. - How global
pattern analysis statistics assess and quantify broad geographic
patterns and trends. - How to use local pattern analysis
statistics to find hot spots, cold spots, and spatial outliers.
Check it out!
And for more Spatial Statistics resources, check out http://esriurl.com/spatialstats
Background Geoprocessing and Spatial Statistics
When it comes to the Spatial Statistics tools in Version 10.0, there are a couple of things that you need to keep in mind when using background geoprocessing. Many of the Spatial Statistics tools have textual output that can be viewed from the progress dialog box and the Results window when the tools are run in the foreground. When the tools are run in the background, you must rely on the Results Window to give you all of that important information (and save it for future use).
Let’s use the Spatial Autocorrelation (Moran’s I) tool as an example. The Spatial Autocorrelation tool returns five values: the Moran’s I Index, Expected Index, Variance, z-score, and p-value. These values are accessible from the Results window and are also passed as derived output values for potential use in models or scripts. Right-clicking on the Messages entry in the Results window and selecting View will display the results in a Message dialog box (as illustrated below). If you execute this tool in the foreground, output values will also be displayed in the progress dialog box.
Optionally, the Spatial Autocorrelation tool will create an HTML file with a graphical summary of the results. In previous versions, you could choose to have a graphic pop up tell you whether your results are clustered, random, or dispersed. A similar graphic summary of your results is still available, but now it is actually saved as an HTML output. This will help us as we share and review our findings in the future. Double-clicking on the HTML file in the Results window will open the HTML file in your default Internet browser.
Also keep in mind that if you are running model tools that you created in ModelBuilder, you will have to make sure that you set the output files (like HTML pages) as Model Parameters. That way they will show up in the Results window.
So, make sure that you remember how important the Results window is for many of the Spatial Statistics tools! And for more resources on using the Spatial Statistics tools, check out our resources page at http://esriurl.com/spatialstats.
Supplementary Spatial Statistics Now Available for Download
There is a new sample script toolbox called Supplementary Spatial Statistics ready for download from the Model and Script Tool Gallery. The toolbox includes two sample script tools that we think you will find very useful. The first tool is Exploratory Regression, which is designed to help you find a properly specified OLS model from a set of candidate explanatory variables. The second tool is Incremental Spatial Autocorrelation, which is designed to help you figure out the right distance band to use for your spatial statistics analyzes. Each tool includes several documents that will help you get started and learn more.
Supplementary Spatial Statistics Toolbox
We’ve also recently added several new tutorials that can also be downloaded from the Model and Script Tool Gallery. To find those resources, and many more, check out http://bit.ly/spatialstats which is always up-to-date with the latest resources for Spatial Statistics.
Network Analyst Barriers in ArcGIS 10
Great blog post on the ArcGIS Desktop blog about Network Analyst Barriers in ArcGIS 10. Find out how things have improved, and download a related model from the Geoprocessing Model and Script Tool Gallery that uses weather data to accurately measure travel times through severe weather conditions.
Image Classification toolbar introduced at ArcGIS 10
A new toolbar, Image Classification, has been introduced at ArcGIS 10 to make image classification tasks both faster and easier (to use this toolbar, you need the Spatial Analyst extension). Expressed simply, the image classification process converts multiband raster imagery into a single-band raster with a number of classes, which you can then use to make thematic maps or for further analysis. Example applications for image classification include landcover mapping and landuse change detection. Continue reading
Spatial Statistics Resources
The Spatial Statistics toolbox contains statistical tools for analyzing spatial distributions, patterns, processes, and relationships. While there may be similarities between spatial and non-spatial (traditional) statistics in terms of concepts and objectives, spatial statistics are unique in that they were developed specifically for use with geographic data. Unlike traditional non-spatial statistical methods, they incorporate space (proximity, area, connectivity, and/or other spatial relationships) directly into their mathematics.
There are a ton of resources about using and understanding Spatial Statistics, and here on the Spatial Statistics team we want to make sure that everyone knows where to find them. We also want to make sure that everyone knows that if you have ArcGIS, you already have the Spatial Statistics toolbox, as well as the source code for most of the tools in it. The Spatial Statistics tools are not an extension, and with the exception of only 2 tools*, every tool in the toolbox is available at all license levels!
We’ve created a shortcut link to the blog that is easy to remember: http://esriurl.com/spatialstats. If you have any questions, there is now a Spatial Statistics Forum on the Resource Center. It’s a great place to post your spatial stats questions so that everyone can benefit from the responses!
Last update: March 6th, 2013
Spatial Pattern Analysis: Mapping Trends and Clusters
These tools can help you summarize and evaluate geographic distributions, identify statistically significant spatial outliers and clusters (hot spots), and assess broad geographic patterns and trends over time. These resources will help you find patterns and relationships in your data, facilitating discussion, contributing to research, and informing decision making.
Short Videos:
- Performing Proper Density Analysis
- Hot Spot Analysis Part 1
- Hot Spot Analysis Part 2
- Hot Spot Analysis Part 3
- Spatial Distribution of Piracy
- Spatial Pattern Analysis of Dengue Fever
Tutorials/Training
- Virtual Campus Training Seminar: Introduction to Spatial Pattern Analysis
- Esri User Conference Technical Workshop: Spatial Statistics Best Practices
- This workshop walks through a real analysis from start to finish, from the gotchas of doing a hot spot analysis to the valuable new exploratory regression tool that helps you explore your data and find a properly specified model.
- Spatial Pattern Analysis in ArcGIS 10 Tutorial
- Hot Spot Analysis Tutorials:
- Hot Spot Analysis Tutorial for ArcGIS 10.1 (New and Improved!)
- Hot Spot Analysis Tutorial for ArcGIS 10.0 (New and Improved!)
- Spatial Statistics ModelBuilder Tutorial for ArcGIS 10
Model and Script Tools
- Supplementary Spatial Statistics Toolbox for ArcGIS 10, currently includes:
- Exploratory Regression
- Incremental Spatial Autocorrelation
- Hot Spot Analysis – Case Study
Presentations
- Spatial Pattern Analysis from the 2011 User Conference
- Spatial Statistics: Best Practices from the 2011 User Conference
Online Documentation
- How Spatial Autocorrelation (Global Moran’s I) Works
- How Hot Spot Analysis Works
- Picking the Right Conceptualization of Spatial Relationships
- What is a z-score? What is a p-value?
Articles and Blogs
Modeling Spatial Relationships Using Regression Analysis
Regression analysis helps you examine, model, and explore data relationships. Ultimately, regression analysis helps you answer “why?” questions: “Why do we see so much disease in particular areas?”, “What are the factors that contribute to consistently high childhood obesity rates?”, and “Why are screening rates so low in particular regions of the country?”. Regression analysis also allows you to predict spatial outcomes for other places or other time periods: “How will improvements to road conditions impact traffic fatalities?” or “How will projected population growth affect the demand for health services?”. These resources will help you learn about basic regression analysis concepts and workflows as they relate to the analysis of geographic data. Learn how to build a properly specified OLS model, interpret regression results and diagnostics, and potentially use the results of regression analysis to design targeted interventions.
- Beyond Where: Using Regression Analysis to Explore Why (New!)
- Virtual Campus Training Seminar: Regression Analysis Basics
- Esri User Conference Technical Workshop: Spatial Statistics Best Practices
- This workshop walks through a real analysis from start to finish,
from the gotchas of doing a hot spot analysis to the valuable new
exploratory regression tool that helps you explore your data and find a
properly specified model.
- This workshop walks through a real analysis from start to finish,
- Regression Analysis Tutorials:
Model and Script Tools
- Supplementary Spatial Statistics Toolbox for ArcGIS 10, currently includes:
- Exploratory
Regression - Incremental Spatial Autocorrelation
- Exploratory
Presentations
- Modeling Spatial Relationships using Regression Analysis from the 2011 User Conference
- Spatial Statistics: Best Practices from the 2011 User Conference
Online Documentation
Articles and Blogs
- Finding a Meaningful Model
- Disease Analysis
- Real Estate Analysis
- Answering WHY Questions
- Tips and Tricks for Finding a Good Model using OLS and GWR
General Resources for Spatial Statistics Users
Presentations
Model and Script Tools
Articles and Blogs
- Background Geoprocessing and Spatial Statistics
- New Chapter in the Handbook of Applied Spatial Analysis
- Understanding Spatial Statistics and Geostatistics
Books
- 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.
*Geographically Weighted Regression (GWR) requires either an ArcInfo License OR the Spatial Analyst Extension OR the Geostatistical Analyst Extension
*Generate Network Spatial Weights requires the Network Analyst Extension
Getting Excited about the UC
The International User Conference is less than 4 weeks away, and here on the Geoprocessing and Spatial Analysis Team we’re already getting excited. The chance to get down to San Diego to meet and work with all of you is something that many of us look forward to all year. We’re already busy polishing our Technical Workshops and bringing our demos together. I’m sure many of you who are attending started planning your sessions, workshops, island times and extracurricular activities in the Gas Lamp district weeks ago! If you haven’t started planning you may want to use the Agenda Search tool to identify sessions of interest to you.
Some sessions that are sure to be popular this year include:
- Intro to Model Builder
- Python Essentials (Introduction / Fundamentals)
- Fundamentals of GIS Analysis (Proximity and Overlay)
- Spatial Pattern Analysis
- Python Scripting and Map Automation in ArcGIS 10
And don’t forget that we are also working on a number of demo theater presentations that should be interesting, so make sure you stop by the Spatial Analysis Island to check them out.
We hope to see you in a session, or in the very least stop by the Spatial Analysis Island and say hi! And if you can’t make it to this year’s User Conference; don’t worry. Many of the slides and video presentations will be posted in the conference proceedings.
This post was written by Kevin Hibma and Lauren Rosenshein, Product Engineers on the Geoprocessing Team
Tips and tricks for finding a good model using OLS and GWR
A user recently posted a great question on the forum about finding a good model using Ordinary Least Squares regression (OLS) and Geographically Weighted Regression (GWR). We know that sometimes finding a good model is not as easy as it looks in a demo, and we spent quite a while putting together some of our tips and tricks to help the user get on the right track. Some of the topics covered include transforming data that is not normally distributed, using coefficient maps from GWR to guide your variable choices, and the use of spatial variables.
Hopefully our response will be a resource to all of you as you use
regression analysis to answer questions and solve problems!
The New and Improved Raster Calculator tool for ArcGIS 10
In ArcGIS 10 the Spatial Analyst toolbox includes a Raster Calculator geoprocessing tool in the Map Algebra toolset. This is not the same raster calculator as in previous versions of ArcGIS, so keep reading to find out what it does, how it’s improved, and where to find more information.
The Raster Calculator geoprocessing tool in ArcGIS 10 is designed to execute a single-line map algebra expression using multiple tools and operators listed on the tool dialog. When multiple tools or operators from the tool dialog are used in one expression, the performance of this equation will generally be faster than executing each of the operators or tools individually.
The Raster Calculator tool has been designed to replace both the previous Raster Calculator from the Spatial Analyst toolbar and the Single Output Map Algebra geoprocessing tool. The Raster Calculator tool is like all other geoprocessing tools; it honors geoprocessing environment settings, it can be added to ModelBuilder, and when used in ModelBuilder it supports variables in the expression. The ability to support variables in the expression makes the new Raster Calculator tool much more powerful and versatile than previous Map Algebra implementations.
The Raster Calculator tool is used to execute Map Algebra expressions inside ArcGIS applications. The Raster Calculator is not supported in scripting because in ArcGIS 10 Map Algebra can be accessed directly when using the geoprocessing ArcPy site-package. This seamless integration of Map Algebra into Python extends the capabilities of Map Algebra by taking advantage of Python and third party Python modules and libraries; making Map Algebra far more powerful than it has been in the past. The Map Algebra language in ArcGIS 10 is similar to 9.x Map Algebra with minor syntax changes due to the integration of Python; most notably case sensitivity.
If you are interested in learning more about the new Raster Calculator tool or about Map Algebra in ArcGIS 10 please go to: ArcGIS 10 Help Documentation.
Post written by Liz Graham, Product Engineer on the Spatial Analyst team
