Every client we have—no matter what industry—will find something important to think about in looking at polling data on food. These polls touch on some of the “universal” questions we ask in market research, such as: How much do consumers trust the safety of products they buy? How much do they trust the companies that…
The Economist ran an article a few weeks ago from which I have borrowed the title of this post. It puzzles over British politicians railing against focus groups for message testing and trying to understand voter sentiment, while continuing to rely on them as heavily as ever. “In an era when voters are monitored, tracked…
Oddly enough, the researchers who most prize scientific rigor (our research colleagues in academia) are the last to have realized that online sampling can be treacherous. An article published in Wired magazine last week describes academic psychologists as “freaking out” because they just learned that a lot of their data, which they source from Amazon’s…
Surveys run the gamut from silly to serious, and from sloppy to scientific. Occasionally we do something silly if a client insists (though we generally advise against it). But we never do sloppy surveys, and we hope you never do them either. Lean as far as possible towards rigor and science within reasonable constraints of…
There is a “user-friendly” feature that some survey platforms now offer, and almost certainly you should avoid it. It is called auto-advance. I had an unpleasant encounter with it in a customer survey I just took. The idea is that, after clicking on an answer, instead of having to move a mouse or finger all…
If you worry that cell phones make it harder to get high quality, thoughtful, and richly detailed data with surveys, stop worrying. New research from a trio of survey measurement scientists (one at the Census Bureau and two at University of Michigan’s Survey Research Center) shows there are no differences in data quality and measurement…
I once heard from an overzealous boss with a Ph.D. in political science that measurement scales should always have an odd number of scale points – the reason being that measurement scales should always have a neutral middle. We sometimes hear this from clients reviewing survey drafts as well: “Shouldn’t every question have a neither,…
Nobody gets really good at market research by taking classes. It comes from learning on the job and in the field from other researchers. That is because researchers are always solving new problems and answering new questions that have never been asked before. That inspired us to make our summer newsletter The Big “How To”…
To get a more robust and representative sample, there are lots of things you can do that will encourage people to participate. You can send them reminders. You can call them. You can invest in snazzy designs to make your survey invitations ever more appealing. But here is one of the best investments you can…
The problem with most business approaches to “analytics” is that they rely on automated, unthinking algorithms. The algorithms scan boatloads of data and generate correlations that are surprising and, therefore, presumably deeply insightful. But in most cases the correlations are not insightful. They are random coincidences, which unfortunately does not stop humans from sharing with…