The chance your online panel study is filled with fraudulent or disengaged respondents is 90% or higher, according to Still More Dirty Little Secrets of Online Panels.
Are you comfortable with doing surveys in which up to half of the responses you’re receiving are fraudulent? Or in which you’re getting a heavily biased group of respondents?
With the drive for speed in research, are you sacrificing getting quality respondents?
There are so many different techniques and approaches available to the consumer insights professional today. But have we simply lost the ability to do good research, even with all these new options?
In articles about the quality of consumer insights, a common opinion is that research quality has gone downhill in recent years. I question that perspective.
The New York Times and CBS News made their own news late last month with the announcement that they would begin using online panels as part of their election coverage polling. This reignited the online/phone quantitative research debate. There’s still no question that phone research is more representative than online research. But does that mean it’s always better?
Are you paying enough attention to the boring part of the research that can destroy your project?
Longitudinal studies can influence how people respond to your questions simply by the fact that you have researched them before. And if you’re not careful, this problem can come about even when you’re not doing a longitudinal study.
In a world where any methodology choice can introduce some bias to your data, it’s imperative to understand how your findings may skew because you chose phone over online (or online over phone, or river sample over panel sample, or any other choice you made).