Geostatistics with Sasquatch

Objectives

1. Do Bigfoot sightings occur randomly across the US?

2. Are sighting locations evenly dispersed on the landscape?

Data

• Bigfoot_pts.shp (BFRO.org)

• NorthAmerica.shp (DIVA-GIS.org)

• US_county_population (U.S. Census Bureau)

The Average Nearest Neighbor tool calculates the average distance from each point to its neighboring point and finds the Observed Mean Distance, Expected Mean Distance, Nearest Neighbor Ratio, z-score, and p-value.

The observed mean distance was approximately 19,064 meters which is less than the expected mean distance which was approximately 47,325 meters. The Nearest Neighbor Ratio is a ration between the observed and expected mean. This tool is used to determine whether data is dispersed or clustered. The Nearest Neighbor Ration is .402836 which is less than one so the data is considered clustered.

The z-score and p-value tells you whether you can reject the null hypothesis or not. Z-score are standard deviations while the p-value is a probability. The p- value is zero which means the null hypothesis is rejected and the data is statistically significant. By having a z-score of -65.3 which is very small means theres an extremely low probability of data below the z-score.

The Nearest Neighbor Distance isn't perfect because its very localized and ignore larger patters which can effect your data and results.

Spatial Autocorrelation (Global Moran's I) tool measures spatial autocorrelation based on both feature locations and feature values simultaneously (ArcGIS). This tool finds Moran's Index, Expected Index, Variance, z-score, p-value. Unlike the Nearest Neighbor tool Spatial Autocorrelation can determine if there is any statistical significance to the amount of clustering. In this data set its considered as clustered.