OTHER PLACES OF INTEREST
Danny Flamberg's Blog
Danny has been marketing for a while, and his articles and work reflect great understanding of data driven marketing.
Eric Peterson the Demystifier
Eric gets metrics, analytics, interactive, and the real world. His advice is worth taking...
Geeking with Greg
Greg Linden created Amazon's recommendation system, so imagine what can write about...
Ned Batchelder's Blog
Ned just finds and writes interesting things. I don't know how he does it.
R at LoyaltyMatrix
Jim Porzak tells of his real-life use of R for marketing analysis.
HOW DID YOU GET HERE?
https:
https:
https:
nettakeaway.com
https:
https:
https:
https:
https:
https:
NAVIGATION
SYNDICATION 
Note to world... is 60% really that big? · 07/19/2006 02:51 AM, Marketing
When reading about huge increases in rates such as this article about using eyetracking to optimize email design, it is wise to remember that age increases are valid only when one knows the base.
For example, the article mentions this quote:
Since Olgivy turned IBM onto the the technology, their click-through rates have increased by 60 percent!
However, they don’t state the original click rate. If it was just 1%, the 60% increase merely raises it to 1.6%.
While this may be great on a large volume mail, if I’m still getting such a low rate, 60% doesn’t mean too much anymore. Was the cost of the eyetrack study worth it? Well, from what the original WSJ article said, the recommendations the study revealed were ones that e-Dialog’s designers had been doing for years.
There are probably some really cool things that the study revealed that Jeanniey Mullen and her gang at Ogilvy didn’t want to reveal, so its worth considering a study like this at some point. Most usability labs in large cities have access to laser eye trackers. Also, consider using even tried and true usability methods to see if your links are too small or hard to find, or if you are using a font too small for older adults or high-res readers to read comfortable, etc. etc.
Read more about Eyetools, one of the better groups out there and the one used by Ogilvy.
And don’t trust large %age increases without the full story of the base rate and how it was calculated. If you don’t see the base, then assume that its too small to be proud of.
(Yes, avid readers, this is again an application of the law of diminishing returns and not the law of large numbers. I also talk about this in one of my rants on stupid stats If you can’t do it right, add more sample! ·
* * *
