How to Run a TURF Analysis

This article describes how to run TURF (Total Unduplicated Reach and Frequency) analysis.

The article describes how to create the below TURF analysis output using bubblegum flavor preferences and showing a portfolio with four alternatives.

Requirements

A data set consisting of at least 100 respondents, ideally many more.
A measurement of the appeal of three or more different alternatives per respondent. These measurements can be from rating scales, historic purchase data, MaxDiff, conjoint utilities, or preference predictions.
All measurement variables converted to a binary variable, where a 1 indicates the person should be counted in whatever is being measured a 0 indicates otherwise. The easiest way to do this in Displayr is to combine the variables as a Binary - Multi Variable Set. Please see Variable Sets for more detail on how to change this in Displayr.
Cases that have any missing data in the measurements will be excluded from the analysis. You may wish to set any missing data values to Include in analysis by using the Missing Data settings in the Object inspector.
For the incrementality plot, it will only work if each TURF output used in it has the same brands as the preceding TURF output.

Method

In the Anything menu select Advanced Analysis > TURF > Incrementality Plot.
In the object inspector go to the Inputs tab.
Select the measurement variable from the Alternatives list.
Specify your desired Portfolio size.
OPTIONAL: To select an alternative to be automatically included in the output go to CONSTRAINTS > Must Include and select the desired alternative from the list. The selected alternative will appear in all portfolios.
OPTIONAL: To select a set of alternatives that can not appear in a portfolio together go to CONTRAINTS > Mutually exclusive set 1 and select the desired alternative from the list. You can select up to Portflop size minus 1 (in our example 4-1 = 3) alternatives per set.
OPTIONAL: Specify the Minimum alternatives per case - the minimum number of alternatives liked in the portfolio. Respondents not reaching the number will not be included in the analysis. By default, the value is set to 1.
OPTIONAL: Specify the Maximum alternatives per case - the maximum number of alternatives liked in the portfolio. Respondents liking more alternatives will not be included in the analysis. The value needs to be less than the number of alternatives in order for it to have any effect. By default, the value is set to 1000.
OPTIONAL: by default, the output contains the top 10 portfolios sorted by reach. To increase the number of portfolios shown in the output go to OUTPUT > Number of portfolios to keep and input the desired number of portfolios to show.