When a plot shows thousands of points, the mass of points can be too dark to show patterns in density. Using the Nonpar Density (nonparametric density) option makes it easier to see the patterns.
Bivariate density estimation models a smooth surface that describes how dense the data points are at each point in that surface. The plot adds a set of contour lines showing the density (Example of Nonpar Density). The contour lines are quantile contours in 5% intervals. This means that about 5% of the points are below the lowest contour, 10% are below the next contour, and so on. The highest contour has about 95% of the points below it.
You can change the size of a nonparametric density contour grid to create smoother contours. The default value is 51 points, which can create jagged contours around dense points.
Press Shift and select Nonpar Density from the Bivariate red triangle menu. Enter a larger value than the default 51 points.
The nonparametric bivariate density report shows the kernel standard deviations used in creating the nonparametric density.