Consumer Research > Choice Models
Publication date: 03/23/2021

Choice Models

Fit Models for Choice Experiments

Use the Choice platform to analyze the results of choice experiments conducted in the course of market research. Choice experiments are used to help discover which product or service attributes your potential customers prefer. You can use this information to design products or services that have the attributes that your customers most desire.

The Choice platform enables you to do the following:

Use information about subject (customer) traits as well as product attributes.

Analyze choice experiments where respondents were allowed to select “none of these”.

Integrate data from one, two, or three sources.

Use the integrated profiler to understand, visualize, and optimize the response (utility) surface.

Obtain subject-level scores for segmenting or clustering your data.

Image shown hereEstimate subject-specific coefficients using a Bayesian approach.

Use bias-corrected maximum likelihood estimators (Firth 1993).

Figure 4.1 Choice Platform Utility Profiler 

Choice Platform Utility Profiler


Overview of the Choice Modeling Platform

Examples of the Choice Platform

One Table Format with No Choice
Multiple Table Format

Launch the Choice Platform

Launch Window for One Table, Stacked
Launch Window for Multiple Tables, Cross-Referenced

Choice Model Report

Effect Summary
Parameter Estimates
Likelihood Ratio Tests
Bayesian Parameter Estimates

Choice Platform Options

Willingness to Pay

Additional Examples

Example of Making Design Decisions
Example of Segmentation
Example of Logistic Regression Using the Choice Platform
Example of Logistic Regression for Matched Case-Control Studies
Example of Transforming Data to Two Analysis Tables
Example of Transforming Data to One Analysis Table

Statistical Details for the Choice Platform

Special Data Table Rules
Utility and Probabilities
Want more information? Have questions? Get answers in the JMP User Community (