MD

MaxDiff Analysis

MaxDiff analysis is a technique for robust ranking of items. It can be used for ranking:

  • Flavours of your product by consumer preference
  • Usage occasions by frequency
  • Aspects of your brand by customer satisfaction
  • Features of a product by importance

MaxDiff is a statistical relative of conjoint analysis. It derives its name from “maximum difference” scaling, also called best-worst scaling.

Traditionally, MaxDiff treats each product as an individual item, whilst conjoint treats products as a combination of attribute levels. As such, conjoint analysis produces rankings for particular products by summing the preference scores for each attribute level of that product whilst MaxDiff produces rankings by polling the respondents directly. However, Conjoint.ly’s novel robust approach to MaxDiff allows for:

  • Testing of multiple attributes in the same survey
  • Brand-Specific combinations of attributes for when each brand is substantially different (to enable that, first create a Brand-Specific Conjoint and then convert it into the MaxDiff variety)
  • Simulation of preference shares, at a highly indicative level

Main outputs of MaxDiff Analysis

Relative importance of levels

Relative value by levels

How do customers rank the potential phone colour options?

Each level of each attribute is also scored for its performance in customers’ decision-making. In our example, navy is the most favourable colour (relative to the other colour options), and displays as positive. Yellow is relatively the least preferred colour and therefore displays as negative. It's important to remember that performance score of each attribute is only relative to the other options shown to respondents. For instance, it is only certain that the colour red will display as negative when it is compared with this specific set of colours (levels) — testing red against a different range of colours, could yield a positive result.

Ranked list of product constructs

Ranked list of product constructs

List all possible level combinations and rank them by customers' preference.

Conjoint.ly forms the complete list of product constructs using all possible combinations of levels. They are then ranked based on the relative performance of the levels that they combine. This module allows you to find the best product construct that your customers will prefer over others.

Market segmentation

Segmentation of the market

Find out how preferences differ between segments.

With Conjoint.ly, you can split your reports into various segments using the information collected automatically by our system: respondents' answers to additional questions (for example, multiple-choice), simulation findings, or GET variables. For each segment, we provide the same detailed analytics as described above.

Works with TURF Simulator

Works with TURF Simulator

Conduct TURF analysis on data using the TURF Analysis Simulator.

TURF analysis aims to find the combination of items which appeals to the largest proportion of consumers. Conjoint.ly makes conducting TURF analysis easy by letting you export your data directly into Conjoint.ly's TURF Analysis Simulator with a single click


How it works

In this methodology, Conjoint.ly presents each respondent with randomly chosen selection of options and asks them to select which option is the best and which is the worst. Each respondent is asked to complete between 12-16 of these questions.

The main output of the method a bar chart of the average preferences. Preference scores are relative, unitless scores that represent the relative preference for each of the items in the MaxDiff. In this chart, items with a higher preference scores are more preferred

An alternative output of the MaxDiff is a barchart showing the percentage chosen best/worst and net percentage. This output shows the number of times each feature was chosen as part of the best option and the number times the feature was chosen as part of the worst option, divided by the number of times the feature was presented to respondents and expressed as a percentage. The net percentage is simply the best percent - worst percent and is another way of measuring preference of respondents to the features. For example, lets say we performed a MaxDiff on soda flavours. Cola was presented to respondents in 100 trials. Of those 100 trials, it was selected the best option 76 times, and selected as the worst option 6 times. Then to calculate the outputs:

  • Best percent: 76/100 = 76%
  • Worst percent: 6/100 = 6%
  • Net percent: 76%-6% = 70%

Now compared to another flavour, Kiwi, which has a best percent of 11%, a worst percent of 70%, and a net percent of -59%, we can infer that respondents prefer Cola over Kiwi.

With Conjoint.ly’s MaxDiff Analysis tool, you can perform a MaxDiff on flavour, pack size, format, and any other attribute you may be looking to test in the same experiment. The preference scores and percentage chosen outputs are presented for each of these attributes separately.

Setting up on Conjoint.ly

To set up a MaxDiff on Conjoint.ly you will need prepare a list of attributes and levels that you wish to test. Then you simply need to add these attributes and levels in the experiment setup screen.

Conjoint.ly also allows you present respondents with additional questions: Multiple choice Likert scale Van Westerndorp Price sensitivity measure Gabor Granger

Only one MaxDiff block may be presented to respondents, but any number of additional questions may be added.

What is the difference between MaxDiff and Conjoint Analysis?

Both techniques are similar in that they present respondents with a set of options and ask them to choose, a method that is based on consumer trade-off decisions that more realistically mimic decisions respondents would make in real life. However, there are some core differences in approach and usage between MaxDiff and Conjoint experiments:

MaxDiff Conjoint
Respondent View
Respondent view of a MaxDiff
Respondent view of a Generic Conjoint
When do we use it? To create a ranking for different alternatives, such as:
  • Features of a product by importance,
  • Aspects of brands by customer satisfaction,
  • Flavours or variants of products by consumer preferences,
  • Usage occasions by frequency.
  • Feature selection for new or revamped products,
  • Marginal willingness to pay for specific features,
  • To test branding, packaging and advertising claims,
  • To find the optimal pricing of products, while taking into account competitor offerings.
Similarities
  • Both techniques are advanced analytical tools, which are constructed based on consumer trade-off decisions.
  • Both techniques result in a output interval scaled utility scores which can effortlessly transformed into ratio-scaled proabilities, so as they can be hierarchised.
  • Both techniques are discrete-choice experiments.
Differences
  • Respondents are asked to chose both their favourite and least favourite alternatives shown.
  • Results are scored by directly polling the respondents.
  • Respondents are prompted to make a single choice across the alternative set , for their most preferred option.
  • Results are calculated through summing all individual level scores.
Example

A car manufacturer wants to learn which is the most preferred car colour among consumers.

MaxDiff analysis is used to provide a robust ranking of the colours according to consumer preferences.

A car manufacturer wants to learn about how much each attribute of a car contributes to a consumers's buying decision.

It also seek for the optimal combination of these components that will increase it's market share.

Complete solution for features and claims research

GC
Range optimisation
Features and claims

Generic Conjoint

Feature and claim selection and measuring willingness to pay for features for a single product.

BSC
Pricing research
Range optimisation

Brand-Specific Conjoint

Feature and claim selection and pricing in markets where product characteristics vary across brands, SKUs, or price tiers.

CT
Features and claims

Claims Test

Test pricing of new and existing consumer goods in a competitive context using elasticity charts, revenue, and profitability projections.

MD
Range optimisation
Features and claims

MaxDiff Analysis

MaxDiff analysis for robust ranking of flavours of your product by consumer preference; or usage occasions by frequency.

PVS
Range optimisation

Product Variant Selector

Feature and claim selection and pricing in markets where product characteristics vary across brands, SKUs, or price tiers.

BPTO
Pricing research

Brand-Price Trade-Off

Test pricing of new and existing consumer goods in a competitive context using elasticity charts, revenue, and profitability projections.

GG
Pricing research

Gabor-Granger Pricing Method

Determine price elasticity for a single product and identify revenue-maximising price level.

VW
Pricing research

Van Westendorp Price Sensitivity Meter

The Price Sensitivity Meter helps determine psychologically acceptable range of prices for a single product and approximately estimate price elasticity.

AB
Concept testing

A/B Test

Perform focussed comparisons between two items to determine which performs better.

MT
Concept testing

Monadic Test

Compare performance of concepts or products though focussed testing

PCT
Concept testing

Product Concept Test

Determine the best concepts through focussed testing

TURF
Range optimisation
Features and claims

TURF Analysis Simulator

Conduct automated TURF analysis on any dataset using Conjoint.ly’s user-friendly TURF analysis tool.

DIY

DIY Experimental Design

Allowing advanced choice modellers to upload their own experimental designs and perform data collection on Conjoint.ly.

FST

Free Survey Tool

Fully-functional online survey tool with various question types, logic, randomisation, and reporting for unlimited number of responses and surveys.