ESRI Spatial Statistics - Six tests to perform on OLS results

I've been quite busy lately - so I haven't had time to post. I hope that this review of spatial statistics will make up for my recent absenteeism!

Earlier this week, I attended a Spatial Statistics seminar hosted by ESRI. What I expected to be a veiled attempt to get users to buy more ESRI extensions was really a review of functions already readily available in ArcView. I was pleasantly surprised and felt that the seminar was worthwhile.

Dr. Lauren Scott was the speaker. She works for ESRI Redlands and has a passion for spatial statistics. It's always refreshing to hear a speaker who has a passion for what she does.

The core spatial tools that were presented were the standard deviation ellipse, hot spot analysis and regression. Most of the seminar focused on spatial regression including ordinary least square (OLS) and geographical weighted regression.

Dr. Scott went over the six quick tests to perform to know if your OLS model is complete; that is, if the model is explaining the dependant variable in the most effective way possible. Once you perform OLS on a variable, these are the six things to examine.

a) coefficients have the correct sign. If the relationship between the explanatory variable and the dependant variable is positive, the coefficient for that explanatory variable should be positive in the final results table. If it is not, the results should be checked.

b) all variables are statistically significant (both probability and robust probability). If the variables are not statistically significant, they should be removed from the analysis because they are not working to explain the dependant variable. The Koenker (BP) test should be significant - this will mean that geographically weighted regression can be performed on the data.

c) the VIF should be below 7.5. If VIF is above 7.5, this means that some of the explanatory variables are redundant and there could be variables that are being double counted in the analysis. The lower the VIF, the better.

d) the adjusted R2 should be high (the closer to one the better), the AIC should be low (the AIC allows multiple models that have the same dependent variable to be compared to one another - if you have two models that for the same dependent variable, the one with the lower AIC is the better model).

e) Jarques-Bera test should NOT be statistically significant. If this value is statistically significant, you are missing an explanatory variable in the analysis.

f) the residuals from the regression should have a random distribution. The more clustered these variables, the poorer the model. Clustered residuals point to explanatory variables that are missing in the analysis.

ESRI Spatial Statistic (Toronto)

Lauren from Redland ESRI has done a great job today by providing easy to understand presentation with the hardest thing to explain in the world. Highly recommend to view the spatial statistic tool that they implement for 9.3 (ArcGIS 9.3 Online help)

GIS can widely use by other field such as Crime (Pocket Men Analysis - to see the pattern of the criminal and provide general area where they will commit the crime), and Health(Try to find out the pattern of disease that spread in the study area) and much more other fields that I would like to explore to. Demonstration in the presentation has open my mind to others in the GIS field how they use the tool smartly :) Can't wait to view the presentation video again!

US police chief leads way on new software

As some of you may know, I’m a big crime buff and I love seeing GIS used to aid law enforcement. I watch cop dramas on television and hope to see a glimpse of GIS used to help solve a big caper.

Police in Edinburgh have received some help from Jim Bueermann, the chief of Redlands Police in California to look at how GIS can be used to find crime hotspots. This will help Edinburgh police focus resources on this area.

I’ve contacted my local police department and I’m hoping to gain further insights on how GIS is used in policing. Watch this blog for further updates of my personal quest!

US police chief leads way on new software - Edinburgh Evening News

ZoomProspector – Business Location Tool

ZoomProspector is a site devoted to aiding businesses in determining site selection for relocation or expansion and helping start-ups find properties.

The site is easy to use and free so it’s a very valuable research tool. As a user, the business would define the information that is important to them (general location, size of market, characteristics of property, labour force information, etc).

When I typed in Cincinnati, Ohio, I was given a map of the location (of course) in addition to some basic demographics about the area including population, labour force activity, and income information. However, the site also provided information about entrepreneurs and innovation (number of patents, venture captial, etc) which could be very important to a start up. Finally, there is information about transportation and travel times. All of these parameters can also be specified in the initial search for a location.

Once a location has been selected, I viewed properties for sale in the area and there were many options to choose from, make the tool flexible and comprehensive. I found a building available for lease on Vine Street and was able to see it on a Google map to get a good idea of the surroundings and was able to find out the lease rate and the amount of space available.

There were so many ways to search on the site and it was quick and performed very well. I think this tool will be very useful to businesses in the US looking to find properties – it would be great to see this type of application for Canada too!

ZoomProspector - Search best communities for business