Clustering Music Test Results

Ask the Research Doctor a question.

Moderators: shawnski, rogerwimmer, jdenver

Forum rules
How do you ask the Research Doctor a question?

Just click on "New Topic" below and then type your question to me. Please put in a Subject and then ask your question in the body.

Your question is submitted annonymously unless you include your name.

Click "Submit" and then check back to find Dr. Wimmer's answer to your question.

If you wish to have a private answer to a question (not posted in the forum), please include your email address. Dr. Wimmer will send your answer directly to you.

Dr. Wimmer maintains an Archive of questions from the forum. Go to http://www.rogerwimmer.com and click on "The Research Doctor Archive" link.
Post Reply
User avatar
rogerwimmer
Posts: 197
Joined: Mon Sep 28, 2009 12:40 pm
Contact:

Clustering Music Test Results

Post by rogerwimmer » Thu Apr 22, 2010 2:25 pm

Roger: Some research companies are using cluster analysis on music test results. Then they are drawing conclusions that relate to the station strategy. What value is there in cluster analyzing the results of a music test? And how does it relate to a station's music strategy? Or does it? Thank you. - Anonymous

Anon: Cluster analysis is a multivariate statistic that simply puts things (variables such as songs) into groups or subsets, where variables in each subset are similar in some way. An easier way would be to use simple correlation to find out which songs relate to each other.

You don't give me enough information about how the cluster analysis results are used to develop a station's music strategy. Strategy for what? Without the information, the only thing I can assume is that the company is suggesting a playlist using the clusters from the analysis – such as playing songs in one hour or one daypart from different clusters to provide a feeling of variety, or playing several songs from one cluster to provide a feeling of "consistency" in sound. I'm not sure without more information.

With the information you provide, there is nothing wrong with using cluster analysis to segment songs into groups or subsets. I just don't know enough about how the results are used to say whether the interpretation is correct or incorrect.


(Want to comment on this question? Click on the POSTREPLY button under the question.)
Roger Wimmer is owner of Wimmer Research and senior author of Mass Media Research: An Introduction, 10th Edition.

Post Reply