## MaxDiff Analyzer

## Overview

The **MaxDiff Analyzer** is an optional analysis program that you log into through your web browser at MaxDiffAnalyzer.com. Each login allows you to upload and use up to 10 separate MaxDiff projects. You must upload scores you've estimated with your MaxDiff/Web system, or via CBC/HB, as the MaxDiff Analyzer does not generate these scores from raw data.

- Automatic rescaling options (e.g. probability, 0-100 scale), with 95% confidence intervals
- Choice simulation capabilities
- TURF analysis for bundle optimization
- Segmentation and weighting

The price for the MaxDiff Analyzer service is $500 per year (allowing one username/password combination to access up to 10 projects). Payment must be made upfront. A maximum of a full year of service may be purchased at this time.

**TURF Analysis**

TURF stands for "total unduplicated reach and frequency." It is an optimization approach for finding a subset of items that "reach" the maximum number of respondents possible. For example, the classic problem is one of choosing which flavors of ice cream to stock in the freezer at a grocery store. The grocer may decide that he/she has limited space and can only include up to 8 flavors of ice cream (out of 30 possible flavors). The grocer wants to maximize the chance that shoppers will find a flavor that they like well enough to buy in the freezer (where "like well enough to buy" means that the preference score exceeds some threshold). If the respondent encounters a flavor he/she likes in the freezer, the respondent is counted as "reached." The problem isn't as simple as including the eight most preferred flavors on average across the sample. Niche flavors that appeal to segments of the population (and that can increase total reach) would be overlooked.

For the ice cream example outlined above, the TURF procedure examines all possible subsets of 8 flavors of ice cream (out of 30 total flavors), and for each set counts how many respondents are "reached." The top sets of 8 flavors that maximize "reach" are listed in the output with the percent of respondents reached shown next to each.

The MaxDiff Analyzer provides three different options for assessing "reach" in TURF:

*First Choice:*The item must be the respondent's top-scoring item to "reach" the respondent.*Threshold:*the analyst supplies a value, indicating a threshold above which a respondent is counted as "reached." If any of the items in the set exceed the supplied threshold, the respondent is considered "reached."*Weighted by Probability:*this method assesses the quality of each subset of items by settings its “reach” equal to the sum of the probabilities of choice for the items in the subset (according to the logit rule). Intuitively, we are finding sets of items that maximize the likelihood that respondents will choose at least one of the items within the set.

The TURF program allows the researcher to specify that certain combinations of features are prohibited from occurring within a set. You can also force certain items to be included in sets.

If the TURF problem becomes too large to search in the tradional way (exhaustive search) the software defaults to a very effective and rapid shortcut heuristic called Stepwise TURF + Swaps.