How to Chart MaxDiff Latent Class Analysis Preference Shares

This article describes how go from a MaxDiff preference shares table:

To a visualization of the preference shares:

Requirements

A document containing MaxDiff respondent-level preference share variables.

Method

Select the preference share variable set in the Data Sources tree.
Drag it onto the page to create a summary table.
From the object inspector , go to Visualization > Pies > Donut (or other visualization type).
OPTIONAL: From the object inspector, go to Data > Data Manipulation and tick Convert to percentages/proportions to convert to %s on the visualization.

With a little code, you can also extract the Total column from the latent class analysis, so that you can plot it.

Having set up the latent class analysis, you can:

From either the toolbar or + in the Report tree, select Calculation > Custom Code.

Paste the code below into the R Code editor:

#specify your max diff latent class analysis
yourlca=max.diff.6
#access the table of preference shares for each class 
pref.shares = yourlca$class.preference.shares
# and pull off the last column which is the Total
pref.shares=pref.shares[, NCOL(pref.shares)]
# sort from highest to lowest
pref.shares.1 = sort(pref.shares, decreasing = TRUE) * 100

Update max.diff.6 with the name of your latent class output. You can get this information by selecting the latent class output, and from the object inspector, go to General > General > Name.

This will create a table with the results from the Total column:
With the table selected, go to Visualization and select the desired visualization type from the object inspector .