NEW EBOOK: Insights That Work - Real research stories from the GRIT Top 50 companies | DOWNLOAD NOW

Rating Scales: A Lack of Drama in 1 Act

speak see hear no evil

 

By Jeffrey Henning

Act 1 – Setting: A Marketing Researcher’s Office

Charlie: How’d that last survey go?

Jessie: Well, the results were pretty clear that consumers preferred Concept C, but it was so different from what the brand had done before that they went with Concept A instead. The brand managers trusted their gut and their past experience more than the research.

Charlie: That’s too bad. Happens sometimes. Well, let’s see about this new questionnaire you submitted.

Jessie: It’s for a new concept test.

Charlie: OK, here you’re using a numeric scale with just the endpoints labeled. According to Krosnick and Tahk in “The Optimal Length of Rating Scales to Maximize Reliability and Validity”, such scales are less consistent, especially with lower educated participants. Let’s use a five-point fully labeled scale, instead. It’s more reliable, according to the research.

Jessie: Well, I always use the 0 to 10 point scale. I’m just more comfortable with it. So let’s keep it.

Charlie: But the research shows…

Jessie: It’s always worked for us in the past. No need to change.

Epilogue

I have a conversation like the above at least once a week. Researchers aren’t so different from the users of our research. It’s easy to ignore research on research in favor of past practices. That’s why I teamed up with QuestionPro to create this video walking people through best practices for interval rating scales. Enjoy!

 

Please share...

Join the conversation

Sign up to our newsletter

Don't miss out...
Get great insights content delivered straight to your inbox.
I agree to receive emails with insights-related content from GreenBook.


You can manage your email preferences or unsubscribe at any time. GreenBook protects your privacy under the General Data Protection Regulation.