Comparing statistical tests and simple rules for validating measurement constructs
In short: Researchers who conducted a simulation study compared the effectiveness of using simple cutoff values against formal inferential tests for assessing discriminant validity. By testing various scenarios involving different sample sizes and indicator patterns, they evaluated how accurately different methods identify whether measurement constructs are truly distinct.
The study found that the heterotrait–monotrait (HTMT) ratio is a robust estimator that performs similarly to the standard constrained PHI approach. This suggests that researchers can rely on these methods to estimate correlations between constructs even when measurements are not perfectly reliable.
The researchers used a simulation study to test these criteria across different correlation levels and loading patterns. However, the findings are based on simulated data, which may not fully capture the complexities of real-world measurement error.
Why it matters: The HTMT ratio is a reliable way to assess if measurement constructs are distinct.
Opens the Intellect+ feed with this card first. Swipe up for the next one.
Sources
- Summary by Intellect · source: Research: Franke and Sarstedt (2019). Heuristics versus statistics in discriminant validity testing: a comparison of four procedures. Internet Research.
To cite this card, link to https://intellectplus.co.uk/app/science-research-comparing-statistical-tests-and-simple-rules-for-validating.
How we source, check and correct cards: Editorial standards.
General information, not professional advice. Spotted an error? Flag the card or see corrections and complaints.
Intellect Plus is a visual educational discovery platform for exploring fascinating facts and ideas. Brain Food, Not Brain Rot. What is Intellect Plus?
Related
More in Science · Latest · A–Z · All topics