@jbgilbert.bsky.social
very closely related! see, e.g. arxiv.org/abs/2409.03502 and edworkingpapers.com/ai24-1082
Testing Whether Reported Treatment Effects are Unduly Dependent on the Specific Outcome Measure Used
This paper addresses the situation in which treatment effects are reported using educational or psychological outcome measures comprised of multiple questions or "items." A distinction is made between...
arxiv.org
April 2, 2025 at 3:11 PM
very closely related! see, e.g. arxiv.org/abs/2409.03502 and edworkingpapers.com/ai24-1082
The key idea is like @klint.bsky.social described. Say I have a new fractions curriculum. If I look at the impact of this curriculum on the state math test, perhaps fractions items improve but geometry items don't. So it's more about our understanding of the intervention than an individual.
April 2, 2025 at 3:10 PM
The key idea is like @klint.bsky.social described. Say I have a new fractions curriculum. If I look at the impact of this curriculum on the state math test, perhaps fractions items improve but geometry items don't. So it's more about our understanding of the intervention than an individual.