Analysis Mode can be used to evaluate whether the spatial pattern of a set of features is clustered, discrete, or random. Analysis Mode uses inferential statistics to establish a null hypothesis in advance when conducting statistical tests, assuming that features or values related to features behave as spatial random patterns. Analyst Result will obtain a p value to represent the correct probability of the null hypothesis, which is used to determine whether to accept or reject the "null hypothesis". The Analyst Result will also get the Z value, which is used to represent the multiple of the standard deviation to determine whether the data is clustered, discrete or random. Calculating probabilities can be important when high confidence data may be needed to make a particular decision. For example, if your decision involves public safety or the law, you may need to justify your decision with statistical evidence.
Analysis Mode allows you to quantify data patterns, perform an initial analysis of the data, and then perform more in-depth analysis. Analysis Mode provides Spatial Autocorrelation, High/Low Clustering, Incremental Spatial Autocorrelation, Average Nearest Neighbor four tools, as described below:
- Spatial Autocorrelation : Spatial Autocorrelation is measured by the Morans statistic based on the spatial position and attribute value of the feature.
- High/Low Clustering : The statistic measures the degree of clustering of high or low values.
- Incremental Spatial Autocorrelation : Spatial Autocorrelation that measures a range of distances and optionally creates a line graph of those distances and their corresponding z-scores. The z-score reflects the degree of spatial clustering, and the peak z-score with statistical significance represents the distance that promotes the spatial process clustering most clearly. These peak distances are usually the appropriate values for tools with the Distance Range or Distance Radius parameters.
- Average Nearest Neighbor : The Nearest Neighbor Index of each feature according to the average Measure Distance between each feature and its nearest neighbor.
Related topics
