Nonspatial analysis

Insights in ArcGIS Online
Insights in ArcGIS Enterprise
Insights desktop

Nonspatial analysis can be accessed using the Action button Action on a map, chart, or table card.

Nonspatial analysis does not consume credits.

The following table provides an overview of each nonspatial analysis capability:

Analysis capabilityDescriptionExample questions

Calculate Ratio

Calculate Ratio uses a simple division equation to determine the relationship between two number variables.

Inputs: Two number or rate/ratio fields

How is it related? How do obesity rates differ between urban and rural residents?

Calculate % Change

Calculate % Change uses initial values and final values to calculate change over time.

Inputs: Two number or rate/ratio fields

How has it changed? What is the percentage of losses or gains for each commodity?

Calculate Z-Score

Calculate Z-Score returns the z-score values for each feature in a dataset based on a chosen field. The z-score is a measure of the distance of each value from the mean, using standard deviation.

Inputs: One number field

How is it distributed? How does the crime rate in a certain district compare to the mean?

Create Regression Model

Create Regression Model is used to model the relationship between two or more explanatory variables and a response variable by fitting a linear equation to observed data.

Inputs:

  • Dependent variable: One number or rate/ratio field
  • Explanatory variables: One or more number or rate/ratio fields

How is it related? Which variables have the most effect on the total sales at each store location?

Predict Variable

Predict Variable uses the linear model created through regression analysis to predict new values in a dataset.

Input: One regression model

How is it related? What are the expected future levels of carbon emissions based on trends in vehicle usage, renewable energy uptake, and economic growth?

Find K-Means Clusters

Find K-Means Clusters categorizes your data into groups or clusters that maximize the similarities within each cluster while maximizing the difference between clusters.

Note:

Find K-Means Clusters can be used to create clusters based on location (spatial analysis), or attribute values (nonspatial analysis).

Inputs: One or more number field

How is it distributed? How are customers clustered by income level? How are universities and colleges clustered by cost?

Next steps

Use the following resources to learn more about analysis:


In this topic
  1. Next steps