Recycling is not just for plastics and paper.
Have you ever had the feeling that the data you collected for one market research project could be repurposed (recycled), if only you had the time? Or have you ever had data from different projects and wanted to find a better way to weave them together, but you weren’t sure how to do analysis across multiple data sets?
Quantitative research means investing a large amount of time and budget. You conduct your study and deliver a report, which is fantastic. But after you get to exhale, perhaps you realize that your data set may have hidden gems buried inside. Now it’s time to learn how to uncover those nuggets to show an even better return on that market research investment.
All research managers care about return on investment. When researchers can show an unexpected level of value, it benefits everyone—the researcher, the research function, and the end client.
Following are two easy ways to recycle data.
Easy Way #1: Combining Two Separate Studies
Years ago, a team I was leading did two projects at the same time for one client. One was a study of consumer laptop owners and the other of IT managers who buy laptops in bulk. For each study our client was a different marketing team—after all, selling laptops to consumers is very different than selling B2B.
Still, there were enough parallels that my team and I were able to go back and look at some of the differences and similarities between results. By looking at both studies we were able to identify some common sources of pain, which led to ideas for universally compelling product roadmap ideas and messaging opportunities. Combining the two studies required extra data analysis, but in this case it was worth it.
Ideally, you have some standard questions (even just profiling ones) that you use in your various studies. Even if you have just a few common variables, some cross-study analysis is possible. And if you have no common variables? You may still be able to take at least a qualitative look at “close enough” items.
|Easy Way #2: Digging Deeper|
A lot of organizations conduct customer satisfaction research, and these surveys are often quite comprehensive. Rarely are all of the data points fully leveraged for insights. In the race to meet project deadlines, the researcher understandably focuses on top priorities—and simply does not have time to exhaust additional ideas.
Asking the following types of questions can help determine new ways to use completed satisfaction research:
- Are there other dependent variables (beyond overall satisfaction) in that data that you’d like to understand more? That is, might it be worth trying alternate dependent variables?
- What are the profiles of customers most and least likely to be satisfied with specific aspects of our products? How are they different?
- Is satisfaction by profiling variable changing over time? In the most recent study, for example, did variations by gender vary less than in past studies? Might this be worth further investigation?
Recycling data in this way is a level of detail that we don’t always have time for when we’re working on an overall satisfaction deliverable, but it adds value and gives the researcher a chance to really shine.
Want Help Recycling Data?
Researchers meet one deadline after another with little time to reflect in between. However, spending time to complete just a few hours of extra data analysis may reveal valuable insights that can change how clients and colleagues perceive market research value.
Rent-A- Researcher can help you temporarily expand your data analysis capabilities with hourly rate researchers. We have over 25 data analysis specialists, people who are experts with SPSS, SAS, R and more. Need some extra help for your recycling project? Just contact Sales@ResearchRockstar.com.
Top 5 signs you may have recycling opportunities:
|I have 2 or more surveys with the same population conducted within 12 months of each other.|
|I have a data set that I analyzed using crosstabs only; further data analysis was not needed for the project deliverables, but could be conducted.|
|I have a data set that yielded some unexpected results; I didn’t have time to explore them before, but I could look to see if these results appear to be anomalies or are in some way consistent with other recently completed studies.|
|I have survey data that was analyzed in aggregate, but I have enough completes in subgroups to support more detailed subgroup analysis.|
|I have a data set that includes responses from a segment we currently consider lower priority; some of the data could be used to explore what actions would be needed to make this segment more attractive.|