Category:Max-Diff

From Q
Jump to: navigation, search

Max-diff is a type of questioning approach in which respondents are presented with lists of items and are asked to indicate which in each list they like the most and which they like the least. It is also known as best-worst scaling.

Max-Diff experiments are questions that present respondents with a series of options and ask them which is best and which is worst. For example, a very simple max-diff experiment may consist of the following two tasks:

Q5a.   Which of these companies do you like the most and which do you like the least?  

Like 			Like 
most			least
○	Apple		○
○	Microsoft	○
○	IBM		○
○	Google		○

Q5b.   Which of these companies do you like the most and which do you like the least? 

Like 			Like 
most			least
○	IBM		○
○	Toshiba		○
○	Dell		○
○	Apple		○

Creating Max-Diff Experiments

See Marketing - Max-Diff - Experimental Design from the Online Library.

Analysis of max-diff models

When a max-diff experiment is selected in the Blue Drop-down Menu a rank-ordered logit model with ties is automatically estimated (see the max-diff pages at surveyanalysis.org for more information about this model).

Refer to the Max-Diff Case Study and Anchored Max-Diff for an examples of the analysis of max-diff experiments in Q.

Personal tools
Namespaces

Variants
Actions
Navigation
Categories
Toolbox