The histogram features in SigmaPlot (Statistics menu, transform language) count the number of occurrences of data in a column in bins defined by the user. Since a two dimensional graph is created (number of occurrences vs. bin number or variable value) this is called a two dimensional histogram. A three dimensional histogram counts the number of occurrences of data from two columns in a grid. The grid is rectangular and defined over the two variables representing the data in the two columns.
This 3D histogram macro uses data from two columns and creates a 3D bar graph of the number of occurrences of the data in a two dimensional grid. The grid is defined from the minima and maxima of the X and Y data and the number of X and Y histogram intervals specified by the user.
As an example consider the X and Y data graphed as a scatterplot.
Figure 1. Scatterplot of bivariate data with two data clusters.
We wish to visualize the relative magnitudes of the data emanating from the lower left corner and the data cluster in the upper right hand corner. Running the 3D Histogram macro gives the dialog
Figure 2. 3D Histogram macro dialog.
The X and Y data can be selected from a dropdown list containing columns identified to possess data. You can specify a specific column in the worksheet to start placing the results or let the macro identify the first empty column. The number of histogram intervals for X and Y can be specified or selected from a list. In this case 15 intervals has been selected for both X and Y.
Clicking OK creates a three dimensional histogram of the bivariate data. Two orientations of the same graph are shown in Figure 3.
Figure 3. The three dimensional histogram of data shown in Figure 1.
The orientation on the left corresponds roughly to the two dimensional data in Figure 1. The orientation on the right shows more clearly the shapes of the two data clusters.
Download the file 3d_histogram.zip and double click on it to obtain the SigmaPlot notebook containing this macro.