A good chart is the best way to understand the law of diminishing returns when it comes to sample size. So for our June 2011 newsletter we built an interactive graph for choosing sample size. It’s cool, educational, and useful. Moreover, it will show you just how mind boggling the numbers behind sampling can be. It may even give you more sympathy for the majority of people who just don’t “get it” or believe it when it comes to statistical sampling.
Archive for the ‘Methods & Tools’ Category
An Interactive Graph for Choosing Sample Size
Thursday, June 9th, 2011Avoiding the Pitfalls of Nutty Net Promoter Scores
Thursday, June 2nd, 2011We have always been big fans of the Net Promoter Score (NPS) metric because it has convinced many firms to begin using customer satisfaction measurement scales that work better and that are tied to what people do rather than what people think. Eleven point scales (with points zero to ten) allow for optimal variation. They are intuitive and appealing: people quickly grasp the idea of rating something on a zero to ten scale, and are familiar with the idea from grade school. They also have a neutral mid-point, which is important for many customer satisfaction and loyalty studies.
But NPS questions do not make sense in many situations. Here’s one we saw last week—it’s a survey sent by Amazon to sellers who call regarding complicated issues with how their products are being displayed on the website or how payments are being transferred:
A Poor Use of the Net Promoter Question
Online Surveys Have Same Accuracy as Phone
Thursday, May 26th, 2011A new study presented by two professors from Harvard University and the University of Massachusetts at Amherst was probably one of the liveliest and potentially disruptive presentations at least week’s annual meeting of the American Association of Public Opinion Research (AAPOR) in Phoenix.
Why? Because their research challenges the beliefs of many AAPOR-ites who disregard most online research as being theoretically indefensible since it is not based on probability sampling. The research presented was based on parallel surveys conducted last year, designed to allow careful comparison of three survey modes: (more…)
How Data Can Highlight Mistakes
Thursday, May 12th, 2011We are often surprised by the number of senior researchers in the market research industry who never touch raw data. Often they don’t even have the tools, since “data processing” is outsourced to lower levels or other countries. It is surprising because we almost always engage in work where getting into the data and puzzling over anomalies or hypotheses yields much deeper insight.
Here is an example of how critical it can be to look closely at your data, and in this case, very early in the data collection process. We launched an online survey last week and got reports back from our sample supplier that incidence was just one-third of what we expected, which would have serious feasibility and cost implications.
But once we looked at their report portal, we saw that for every qualified respondent completing the survey, two qualified respondents quit before finishing. That’s an unusually high ratio of “suspends” as we call them. So what was the problem? Were we just getting lousy respondents who did not want to seriously participate in a survey? Was the survey was too difficult, tedious, boring, or confusing? One source of answers (rarely examined) is to look at the data question by question to identify where in the survey people are quitting.
The story in this data: Something is wrong with your survey
Don’t Be the ‘Me’ Generation with Your Surveys
Wednesday, May 4th, 2011One reason that some people dislike surveys (okay, I may be projecting) is that too many surveys have the Me Generation attitude:
Enough about you, the customer, and what you need. What about ME? Do you like me? How much do you like me? Would you recommend me to your friend? Please let me know, because we need to track our satisfaction scores. It helps us build our metrics and our dashboards. And if you like me enough, I get a big bonus. Hurray for me!
Who are your customer satisfaction surveys really about?
Reasons to Avoid Grid-Format Questions
Saturday, April 16th, 2011Among the many sources of potential error that can affect surveys are respondents themselves. They sometimes misinterpret questions, respond in socially acceptable ways, or give “easy” answers in hopes that a more interesting question is just around the corner.
This is not to say they are bad or fraudulent respondents. Research shows that the vast majority of survey respondents are careful, thoughtful, and truthful in how they answer survey questions. The problem with respondent error, it turns out, is poor survey design, which may involve biased or ambiguous questions, tasks that are too complicated or boring, surveys that are too long, and so on.
Recent research shows that grid-style questions that look like this:
or this: (more…)
Overcoming Your Math Curse
Friday, March 18th, 2011
Learning the math behind market research is not easy because there is no programmatic way to master it as a body of learning. It is not like algebra, geometry, calculus, or statistics in high school or college. It is complex and multifaceted and draws upon nearly every area of theoretical mathematics, but it must be continually adapted to the needs and practical problems of measuring and predicting customer behaviors and attitudes.
So it requires both (1) a rigorous foundation in mathematics and (2) years of experience to understand how it gets re-worked and applied to the real-life questions of market research. And even the rigorous foundation needs to be continually reinforced and expanded as the scope of our capabilities expands. Twenty years ago, who would have thought that Bayesian statistics and Monte Carlo simulations would become so central to our work? (more…)
The ABC’s of CBC: Understanding Conjoint for Market Research
Thursday, March 10th, 2011Our March 2011 newsletter focuses on conjoint research, which we consider to be one of the most clever and powerful techniques of survey research. Why? Because it allows us to build working models of decision-making.
Conjoint works by presenting people with scenarios that are more like the real-life trade-offs they always make. For example, instead of just asking a respondent about the importance of price, we ask them to make decisions about price, where price varies based on other attributes that are important to them. (more…)
When to Use Paper Surveys
Thursday, March 3rd, 2011
One might think that with evolving technologies, the old-fashioned ways of doing research, like using paper and pencil, might disappear. But it turns out that paper surveys are not dead, and here is a nice example that dramatically illustrates their value.
As newly-appointed director of market research for the American Marketing Association in Chicago, I oversee efforts to develop and organize events related to market research. I also oversee efforts to measure, track, and analyze customer satisfaction for all other events and activities sponsored by the AMA. For the past few events, the AMA collected feedback via an online survey sent by e-mail immediately after the events. They were also using a less-than-stellar do-it-yourself survey tool that promises to deliver “actionable insights!” at the click of a button.
The results were abysmal. (more…)