This article explains how to do a Mixed-Mode Cluster Analysis in Displayr. Mixed-Mode Cluster Analysis is a clustering technique that permits all different question types available in Displayr as inputs to the analysis.
Requirements
- A series of questions in your data set that you want to use as inputs to the Mixed-Mode Cluster Analysis. You can use any of the Displayr variable structures as inputs to the analysis.
Please note these steps require a Displayr license.
Method
- From the toolbar, select Anything
> Advanced Analysis > Cluster > Mixed Mode Cluster Analysis.
- OPTIONAL: If you have multiple data sets in your document, you'll be prompted to select the data set that you want to use for the analysis. If so, select a data set.
- Select variables/variable sets from the Available data list on the left to include as inputs to the analysis. Selected variables or variable sets will appear on the right in the Data to display list.
- Select the number of groups/clusters:
- Work out number of groups automatically - Displayr will automatically work out the number of clusters/segments using the Bayesian information criterion.
- Specify the number of groups - enter the number of groups/clusters you want to create.
- OPTIONAL: Select a Filter if you want to run the analysis based on a filtered subgroup of respondents.
- OPTIONAL: Select a Weight to weight the the input data.
- Click Create Mixed-Mode Cluster Analysis.
A new single response variable is added to the bottom of the data set called "Latent Class Analysis" with a date/time stamp in the variable label. You can use this variable just like any other categorical variable in your analyses.
To modify the analysis, select the Mixed Mode Cluster Analysis output, and then from the object inspector, click Data > Data & Assumptions > Modify. You can then modify your inputs as needed and rerun the analysis by clicking Modify Mixed Mode Cluster Analysis.
To run a diagnostic report on your analysis, select Anything > Advanced Analysis > Cluster > Diagnostic > Analysis Report.
The results are as follows:
Next
How to Analyze Data by Groups/Segments
How to Do Latent Class Analysis
How to Create a Segmentation Comparison Table
How to Do K-Means Cluster Analysis
How to Save K-Means Cluster Membership
How to Do Hierarchical Cluster Analysis in Displayr
How to Create Diagnostic Reports for Latent Class, Mixed Mode Trees, and Mixed Mode Cluster Analysis