This function produces a table of parameter statistics for both Latent Class Analysis and Hierarchical Bayes outputs from a choice-based conjoint model. With latent class analysis, it is a table containing parameter estimates and significance-testing statistics. With hierarchical Bayes, it is a table containing sample statistics of the mean and standard deviation parameters for the distribution from which individual coefficients are sampled. For more information on how to interpret this output, see this blog post, which was written for the closely related MaxDiff analysis.
Note that with Hierarchical Bayes, numeric variables are shown as scaled (this is done to improve model sampling). The prefix "Scaled" is added to numeric variable names. To descale the numeric variable coefficients, standard deviations, and standard errors, multiply them by the multipliers that can be obtained by creating a new R output and typing in choice.model$numeric.scaling into the R CODE editor (choice.model needs to be replaced with the name of the choice model output) and clicking calculate. The output will contain a list of multipliers to be used for each numeric variable.
The table below shows parameter statistics from a Choice Modeling - Latent Class Analysis output:
The next table shows parameter statistics from a Choice Modeling - Hierarchical Bayes output:
Requirements
A Latent Class Analysis or Hierarchical Bayes output from a choice-based conjoint model
Method
To create the Parameter Statistics table:
1. Select model output.
2. Select Anything > Advanced Analysis > Choice Modeling > Diagnostic > Parameter Statistics Table.
Alternatively, in the Object Inspector of the model output, select DIAGNOSTICS > Parameter Statistics Table.
Technical details
Whenever Hierarchical Bayes analysis is run with multiple classes, an attempt will be made to match class labels between chains (note that it is often not possible to match class labels). If this succeeds, or if only one chain was specified, one set of mean and standard deviation parameters will be shown for each class in the parameter statistics table. In addition, class size parameters will also be displayed. If this attempt is unsuccessful, the parameter statistics table will not be able to be shown.
References
McLean, M. W. (2018, July 24). How to Use Hierarchical Bayes for Choice Modeling in Displayr [Blog post]. Accessed from https://www.displayr.com/how-to-hierarchical-bayes-choice-model-displayr/.
Yap, J. (2018, January 16). Checking Convergence When Using Hierarchical Bayes for MaxDiff [Blog post]. Accessed from https://www.displayr.com/convergence-hb-maxdiff/.
Next
How to Do the Statistical Analysis of Choice-Based Conjoint Data