0
$\begingroup$

Effect sizes are categorized into 'Standardized effect sizes' and 'Unstandardized effect sizes'.

My question is, Vargha-Delaney A falls in which of the categorizes? does it cound as standardized effect size?

$\endgroup$

1 Answer 1

1
$\begingroup$

I'll use the definition from The Analysis Factor:

The first type is standardized. When most people talk about effect size statistics, this is what they’re talking about. Standardized effect size statistics remove the units of the variables in the effect.

VDA would then fall under the definition of standardized effect size. It reports a probability of an observation from one group being larger than an observation from the other group. The original units of the measurement variable are not used.

Also, it is "standardized" in the sense that it ranges from 0 to 1. This is similar to the behavior of statistics like r, r-squared, Cliff's delta, that range from -1 to 1 or 0 to 1. Note that Cohen's d is considered a standardized effect size, but has no upper bound. Likewise, Cohen's w.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.