Scatter Plot analysis identifies relationships and outliers across two variable combinations. These types of plots are used to investigate the possible relationship between two variables. Often, inferences can be made depending upon the cluster of points within the scatter plot::
- There may be positive correlation if the points are clustered in a band running from lower left to upper right.
- There may be negative correlation if the points are clustered in a band running from upper left to lower right.
If a straight line or curved can be drawn through the cluster of points on the graph, the stronger the relationship between the two variables.
The scatter plot analysis can apply to any type of numeric data, using SAMPLE to plot a random selection of data points across two or three dimensions. The axes are scaled based on the range of data returned from the sample size specified. A practical limit has been set at 30,000 data points.
The Scatter Plot analysis is parameterized by specifying the databases, tables and columns to analyze, the options unique to the Scatter Plot analysis, the desired results, and expert options.