Login  |  Register          Free Newsletter Subscription
Magazine Subscription
Making Marketing Work   


Link This | Email this | Blog This | Comments (1)


Are You Using Control Groups?
May 16, 2008

As a marketer, you are probably experimenting with a variety of different types of marketing techniques. Perhaps you are varying different offers for different demographic segments. Maybe you are experimenting with personalized messaging.

Whatever you are doing, it should include control groups.

What’s a control group? It’s a dedicated sample of your campaign that is unchanged. This allows you to compare whatever changes you’ve made to your existing strategy on an applies-to-apples basis. Otherwise, you have no way of knowing what other factors might be influencing the results.

For example, say you decide to change up your messaging and increase the size of your postcards from the standard 4.25 x 6 inches to an oversized 6 x 8.5 inches. Your response rate goes up 8%. What caused the jump? Was it the change-up in messaging? Or was it the increase in postcard size? Increasing the size of the postcard has a cost, both in print and postage. Changing up the messaging may not. It’s important to know what percentage of your mailing was influenced by each.

A better approach is to split the mailing into four equal segments:

  • One quarter is your old mailer.
  • One quarter is the old size, but with the new messaging.
  • One quarter is the old message with the new size.
  • One quarter is the new message, new size.

Split the list randomly so there is no unseen influence in recipient base.

This will tell you exactly which elements had what impact on your response, as well as how the combination of elements may have amplified the message over any single element alone.

The use of control groups is a “best practice” that all marketers should be implementing. If you aren’t, your next program is the place to start.
Have questions? Comments? I'd love to hear from you. You can email me at htollvr@aol.com. For more information on primers for marketers and small businesses on digital, 1:1, and Web-to-print technologies, visit www.digitalprintingreports.com.

Posted by Heidi Tolliver Nigro on May 16, 2008 | Comments (1)


May 18, 2008
In response to: Are You Using Control Groups?
Richard Romano commented:

Good point; control groups are vital in scientific research and experimentation. These are usually the folks in medical experiments who get placebos while the rest of the sample gets the good stuff (well, maybe...). The idea is to isolate or "control" for one particular variable. Seems appropriate in a discussion of variable-data printing!





POST A COMMENT
Display Name or Registered Users Login Here.
Please restrict submissions to less than 7,000 characters (including any HTML formatting).

Before submitting this form, please type the characters displayed above. Note the letters are case sensitive:


Advertisement

Advertisements



SPONSORED LINKS


About Us   |   Advertising Info   |   Site Map   |   Contact Us   |   Free Subscriptions   |   Affiliate Links
©2008 Reed Business Information, a division of Reed Elsevier Inc. All rights reserved.
Use of this Web site is subject to its Terms of Use | Privacy Policy
Please visit these other Reed Business sites