GIS3015 L5: Spatial Distribution

This week we were given a reprieve from Corel Draw--thank goodness! The challenge this week was to:

• Define key spatial statistics terms

• Know what questions to ask about your data before choosing an analysis tool.

• Examine the spatial distribution of a dataset to identify clusters and spatial relationships in the data.

• Recall the properties of a normally distributed dataset.

• Interpret a histogram to determine the frequency distribution dataset.

• Find outliers in your data using a semivariogram cloud, Voronoi map, histogram, and normal QQ plot.

• Use a trend analysis graph to identify patterns in your data.

• Assess which analysis tools are appropriate given the spatial distribution and values of your data.

In other words, we are doing STATS this week in GIS3015! I cannot tell you how much fun I have been having--really. 

I completed the ESRI web course on, "Exploring Spatial Patterns in Your Data Using ArcGIS". An excellent course that included finding and using the Geospatial Statistical tools.  This included: Geostatistical Analyst Tools and Measuring Geographic Distributions such as the Mean Center and Median Center. I enabled the Geostatistical Analyst Toolbar  .  On the toolbar I selected "Explore Data" and then used the QQ plot.  A QQ plot displays the relationship between the distribution of my data and a normal distribution. I had to ensure I selected the layer to be evaluated; temperature for this exercise. I was looking for outliers, such as any point off the normal distribution, either too high or too low.  

In this QQ plot above, the data falls mainly on the normal distribution line. However, at the extreme right of the plot (see below image), you can see one point that is far above the normal distribution. This is our outlier.

This was a very good exercise, as an introduction to all the Geospatial Anaysis tools available to us. However,I am sure I will spend many more nights reviewing all these tools and my favorite subject, Statistics...