Choice-Based Conjoint analysis in modern reports
Choice-Based Conjoint tiles in modern reports enable you to measure how respondents make trade-offs between product attributes, and use those trade-offs to simulate how different product configurations would perform in a competitive market.
The Choice-Based Conjoint tile displays the results of the conjoint analysis. You can switch between the chart view and table view to examine the results. The tile also displays a convergence plot that shows whether repeated iterations of the algorithm converged, indicating that the analysis results are reliable.
For example, if you want to understand which combination of brand, scent, format, and price would capture the largest share of laundry detergent buyers, the Conjoint Market Simulator lets you build scenarios, adjust the attributes of competing products, and instantly see how preference shares shift.
The chart view
A Bar chart the default visualization for Choice-Based Conjoint questions. Use the chart to quickly identify which attribute drives the most preference (the attribute with the widest spread of bars) and which levels within each attribute are most and least preferred.
The chart displayed Zero-Centered Difference (ZCD) values. A ZCD value represents how much a level contributes to consumer preference. ZCD values are shown for each attribute (brand, price, etc.) and level (Store Brand, EverClean, etc.) specified in the Choice-Based Conjoint question.
These are the key points for interpreting ZCD values:
- A positive ZCD value indicates that consumers prefer this level more than the average level within that attribute.
- A negative ZCD value indicates that consumers prefer this level less than the average level within that attribute.
- A ZCD value near zero indicates that consumers feel relatively neutral about this level.
- To identify the most compelling product configuration, select the level with the highest ZCD value from each attribute and bundle them together.
- You can compare ZCD values for levels within the same attribute. Do not compare ZCD values for levels from different attributes.
The table view
The table view displays the same attributes, levels, and ZCD values as the bar chart in a crosstab. The table view includes two additional results that apply to attributes:
- Importance: How much influence an attribute has on respondents' overall choices, expressed as a percentage. Higher importance means the attribute drives more of the decision.
- Relative importance: Relative importance expresses each attribute's importance as a percentage share of the total importance across all attributes, making it easy to compare which attributes matter most at a glance
The Convergence plot
The convergence plot shows the stability and reliability of the statistical model over time. The plot tracks whether the repetitions of the algorithm have settled on a consistent answer. The following chart shows convergence, which is apparent from the small amount of variation on the y-axis (Mu) for each attribute and the "hairy caterpillar" appearance of the chart. This allows you to be confident that your recommendations and business decisions are based on the data rather than "noise."
The Conjoint Market Simulator
The Market simulator is a Microsoft Excel workbook file that you can download from the choice-based conjoint tile. It includes the market simulator plus all of the Zero-Centred Difference data that's available in the report tile. It also includes a copy of the convergence plot.
You can create between 2 and 10 alternatives for your simulations, which are bundled combinations of attributes that make up a product or service. Use the drop-down in each cell to select the attribute you want for the alternative.
If you want to understand which combination of brand, scent, format, and price would capture the largest share of laundry detergent buyers, the market simulator lets you build scenarios, adjust the attributes of competing products, and instantly see how preference shares shift.
For information about Choice-Based Conjoint and how to perform Choice-Based Conjoint analysis, see Conjoint analysis.