MeasuringU

We’re often asked how large the sample size needs to be for #UXresearch using the System Usability Scale (SUS). It depends … measuringu.com/sample-sizes-f…

How do changes in standard deviation affect sample size estimation? Even somewhat modest changes to standard deviations can have large effects on sample size estimation. measuringu.com/how-do-changes…

Designing for Dependence: When UX Turns Tools into Traps. (UX Magazine) uxmag.com/articles/desig…

As a #UX researcher, you might have been exposed to the idea that when sample sizes are small you shouldn’t report numbers or percentages. In this article, we demonstrate that there are counterarguments to that assertion. measuringu.com/should-you-rep…

Some variables cannot be observed directly. Trust is one example; it can only be measured through inference. Such variables are hidden (latent). measuringu.com/understanding-…

Most #usability tests mix formative and summative goals (finding problems and gauging performance), so there’s often a need to balance the sample size requirements. measuringu.com/larger-sample-…

Looking for a compact way to summarize #survey results? Try a banner table. bit.ly/40Sr2hS

When we ran a study to refine three methods for measuring tech savviness, the least promising approach was a knowledge quiz. measuringu.com/refining-tech-…

In the 20 years of existence of MeasuringU, we’ve made significant contributions to developing and evaluating #UXresearch methods and metrics. measuringu.com/20-years-of-me…

A study of numeric rating of the intensity of 12 verbs found four groups—High intensity decreasing (e.g., tanked); Low intensity decreasing (e.g., fell); Low intensity increasing (e.g., grew); High intensity increasing (e.g., spiked). measuringu.com/change-verbs/

Banner tables are well known deliverables in market research but are less well known to #UX researchers. bit.ly/40Sr2hS

Organizations rated as mature in #UX are almost twice as likely to have a dedicated #usability space as those rated as less mature. measuringu.com/build-usabilit…

There has been a lot of #research on using different numbers of scale points. We’ve summarized some of the most important findings from 12 studies. measuringu.com/three-points/

We know from earlier research that people are less likely to agree to extremes. This holds true, though only slightly, when you simply change “very satisfied” to “extremely satisfied.” measuringu.com/very-vs-extrem…

In a comparison of an item sequence that varied from 5 to 11-point scales versus the same item sequence with only 5-point scales, there were no significant differences in response behavior and only 13% of respondents noticed the difference in item formats. measuringu.com/changing-the-n…

In this article, we report the results of four studies conducted to validate using technical activity checklists to classify participants in #UXresearch into different levels of tech savviness. measuringu.com/classifying-te…

Would you expect to get similar results with numbered and unnumbered versions of the Single Ease Question (SEQ®)? Here’s what we found. measuringu.com/comparison-of-…

An example of convergent evolution in #UX methods, User-Centered Design (UCD) evolved from earlier usability engineering practices while Design Thinking evolved from more traditional professional design practices. measuringu.com/ucd-and-design…

One consequence of our finding higher dropout rates when requiring webcam usage and thinking aloud in unmoderated #usability studies is #UX practitioners who need 20 participants to complete a study should invite at least 40. measuringu.com/does-ta-increa…

To investigate the effect of including images in card sorts, we conducted an experiment with 623 participants assigned to one of three card sorting conditions: Text-Only, Image-Only, and Image+Text. measuringu.com/do-images-make…