NPS BASICS AND BEYOND
Tread Carefully When Weighting NPS Results to Avoid Bias
WEIGHTING NPS RESULTS

Tread Carefully When Weighting
NPS Results to Avoid Bias

key takeaway

Weighted NPS results may aid understanding, but they can also introduce bias, create confusion, and keep you from taking needed action. Tread carefully.

Best Practice

If your survey sampling tactics produce survey results that over- or under-represent portions of your customer base, you may want to consider weighting your results. Public opinion pollsters commonly use this tactic when they adjust by demographic factors to better match the likely voting population, for example. While the practice can create more accurate polling that predicts behavior, it can also have the opposite effect by skewing the results inappropriately or raising questions of results tampering.

The same applies to customer experience data, whether survey results or operational performance information. If you are present in 50 countries, are all represented in your sample? If you are going to present an average result for NPS or for on-time delivery across your entire company, should your sample be weighted by the revenue in each country? Our suggestion is that it should, everything else being equal. If Brazil represents 13% of your revenue, it should have that weight in your result calculations.

One of the other factors that may need to be compensated for is data collection mode. You should do your best to understand whether collection of data via text messages, email, telephone surveys or other methods bias results in some way. In a perfect world, you should do this by so-called ‘A / B testing’. This means you randomly assign customers to different survey methods and compare the results. If there are only small differences, don’t worry about them. If the differences are substantial, they need to be compensated for in your results.

go beyond basic nps reporting

It’s very common for colleagues and executives to challenge the data from NPS programs, even when these foundational best practices are in place. Those challenges often expose the hard truth that customer experience data is not good enough. Even smart analyses and weighting strategies aren’t enough to overcome the fundamental deficits in the underlying data set. There’s no way around it: You’ll need more complete data to build a program that delivers real outcomes. To get there, download our guide, take our comprehensive training course, or read about the future of NPS.

REPORT

The Complete Guide to NPS Basics and Beyond

TRAINING

Leading an Outcome- Oriented
CX Program

REPORT

The New NPS
Manifesto

REPORT

The Complete Guide to NPS Basics and Beyond

TRAINING

Leading an Outcome- Oriented
CX Program

REPORT

The New NPS Manifesto

ABOUT OCX COGNITION

OCX Cognition delivers the future of NPS. We ensure customer experience success by combining technology and data science with programmatic consulting. In our Insights section, we present a comprehensive and evolving collection of resources based on our research and expertise, collected for CX leaders committed to delivering business outcomes.