Effect size
A standardized measure of how large a study's result actually was (commonly expressed in standard deviations), used to compare findings across studies and to avoid mistaking a modest result for a dramatic one.
Defined in 2 GAGE programs, which carry 3 distinct definitions of it. The wording above is taught in AI Literacy & Professional Conduct.
How each discipline defines it
The same term does different work depending on who is using it. These are the definitions as each program teaches them, unedited.
A measure of how large a reported difference actually is, as distinct from whether it is statistically detectable at all; used in a synthesis matrix alongside a reported mean to judge whether a headline comparison between two methods reflects a meaningful practical gap or one that is technically present but small enough not to drive a real engineering decision on its own.
A standardized measure of how large a study's result actually was (commonly expressed in standard deviations), used to compare findings across studies and to avoid mistaking a modest result for a dramatic one.
The actual magnitude of a reported difference or improvement, as opposed to whether that difference cleared a statistical significance threshold. A statistically significant result can still have an effect size too small to matter for an engineering decision, per Section 3K.
Where it is taught
The exact lessons this term appears in. The first 7 topics of every program are free with a free account.
- What the Evidence Really Says About AI and Learning · Bonus: AI for Educators, AI Literacy & Professional Conduct
Terms it appears with
Not an alphabetical neighbourhood: these are the terms taught in the same lessons, ranked by how often they appear together.