Consultants Highlight Nielsen's Sample Size/Effectiveness Conundrum
June 13, 2014 at 11:00 AM (PT)
NIELSEN is being called to account for what some believe is a grave lack of sample size and for the inordinate length of time it takes to accrue it. In a blog post TODAY (6/13), MARK RAMSEY cited a research project he conducted for a station in a "relatively small market' that captured the sentiments of 600 people. To do the same through its diaries, RAMSEY claimed NIELSEN takes up to two years to generate a similar-sized sample.
Even more telling, he brought up the observations of TRACY JOHNSON, who discovered that in a market of a station he consults, the total in-tab for Women 18-34 was 147 respondents. "Now if you take those 147 “voters” and divide them by age and sex and ethnicity and then spread out their behaviors over many dayparts, dozens of stations, and, potentially, dozens of online streams, you have data which is militantly opposed to accuracy and is, rather, an illusion," RAMSEY said. "And not a very good one, at that.'
JOHNSON added more detail: "In a Top-20 market with a population over 2 million, 58 women age 18-24 carry meters that determine the ratings for all of the stations in the market. Millions of advertising dollars are spent based on this research. And our broadcasters are paying how much for this data? Really? We collectively sell this to our advertisers and they actually have confidence that their marketing investment is in good hands?"
"What’s the answer?" RAMSEY asks aloud. "Not just more sample. But more emphasis on effectiveness. A stronger obligation to make the buy work for the client – and that buy can work no matter how big or small NIELSEN says your ratings are. Isn’t this why so many spoken-word stations perform much better in revenue than their ratings would suggest? Prove and argue effectiveness. Because as accountability proliferates, more and more clients will be buying what works at the right price rather than whatever the ratings magician pulls out of his magic hat."