Topics
Topics
Why You Should Not Compute Medians for Individual Rating Scales
Say you collect rating scale data from dozens of users across ten apps. To analyze the data, you compute medians because you learned that rating scale data isn’t interval or ratio data. The medians of all ten apps end up the same. They’re all 4! If you rely on the medians, you’d conclude the apps
An Intro to Bayesian Thinking for UX Research: Updating Beliefs with Data
“That design will never work.” You may have had that thought before you even ran your first participant in a usability test. If you’ve seen enough users struggle and conducted enough usability tests, then you probably have some idea about how well or poorly a task attempt may go for prototypes or even commercially available
An Introduction to Effect Sizes
The completion rate jumped from 20% to 80%. That’s a large effect size. If it had gone from 20% to 21%? Much smaller effect. It’s easy to get caught up in the mechanics of significance testing and p-values. But even before those tools existed, researchers were measuring effect sizes. Effect sizes remain fundamental to understanding
Sample Sizes for Comparing UX-Lite Scores
The UX-Lite® is a relatively new metric, but it is versatile, short, and increasingly popular for UX research. It measures perceived usability and usefulness with just two items. But if you’re using the UX-Lite to compare products or to see whether you’ve improved over time, what sample size do you need? Yes, the sample size
UX and NPS Benchmarks of Clothing Websites (2026)
It’s hard to beat the convenience of shopping for clothing online. You don’t have to worry about when the store will close or finding parking, and getting a price comparison with other stores is just a few clicks away. On websites, you can easily search for clothing using keywords, and it’s simple to see the
UX-Lite Sample Sizes for Comparison to a Benchmark
The UX-Lite® is a relatively new but increasingly popular metric for UX research. Its two items generate an overall score and subscale scores on ease and usefulness from 0 to 100. The UX-Lite predicts future product usage as well as or better than the original and longer Technology Acceptance Model (TAM). The ease score also
UX and NPS Benchmarks of Mass Merchant Websites (2026)
People spend a lot of money (and time) on online purchases, most of that on what we call mass merchant retail websites. The US Census Bureau estimates Q3 2025 retail e-commerce sales at $310B (15.8% of total retail sales that quarter). Spending continues to grow but is tempered by inflation, making shoppers more economically pessimistic
UX-Lite Sample Sizes for Confidence Intervals
The UX-Lite® is an increasingly popular UX metric. There’s a reason for its popularity. It’s a simple two-item questionnaire that measures perceptions of the user experience of any interface (product, app, website). Its two five-point items are combined and scaled to generate an overall score and subscale scores on ease and usefulness from 0 to
How the SEQ Correlates with Other Task Metrics
While task completion and task time are the default choices for measuring task effectiveness and task efficiency, the methods used to capture people’s feelings about an experience certainly seem more varied. But after measuring post-task perceptions for decades, we’ve found that a simple seven-point item does a good job of capturing not only perceptions of
48 UX Metrics, Methods, & Measurement Articles from 2025
Happy New Year from all of us at MeasuringU®! In 2025, we posted 48 articles and continued to add features to our MUiQ® UX testing platform to make it even easier to develop studies and analyze results. We hosted our 12th UX Measurement Bootcamp—a blended virtual event attended by UX practitioners who completed a combination
How Much Does Satisfaction Correlate with Ease?
Satisfaction is different than ease of use. But they are both attitudes. We provided the conceptual foundation for what satisfaction is, how it differs from perceived ease of use, and how both can be collected at the overall product level (also called the study level) or at the task level. So, while we know they
What Are UX Research Deliverables?
As professionals, we’re judged on what we produce. So-called deliverables are the artifacts produced by researchers. But what are UX research deliverables? Deliverables are almost always a digital record of inputs, outcomes, and recommendations in a document or presentation. But delivering documents and presentations fits the description of just about all knowledge worker output, so