Skip to content

Bayesian Yoking Procedure

Research Method · All research methods
Evidence · 1 claim (1 for) · 1 study (1 causal), q2 · 0 of 1 report an effect size · 1 claim rests on one study

Description

A novel methodological approach in which each yoked participant observes the responses of an "ideal Bayesian learner" personalized to have that participant's individual prior beliefs. It proceeds in three steps: (1) creating profiles of children's prior belief distributions from pretest data using a hypothesis space of four competing theories (size, material, mass, random guessing) and k-means clustering into six profiles, (2) performing trial-by-trial Bayesian posterior updating for each prototypical profile across the 34 learning trials, and (3) assigning new learners to the best-fitting profile via lowest Wasserstein distance, so yoked children see the responses they would most likely have generated themselves.

Accounts

  • Bayesian Yoking Procedure: a three-step computational method for personalized yoked control conditions: A novel methodological approach in which each yoked participant observes the responses of an "ideal Bayesian learner" personalized to have that participant's individual prior beliefs. It proceeds in three steps: (1) creating profiles of children's prior belief distributions from pretest data using a hypothesis space of four competing theories (size, material, mass, random guessing) and k-means clustering into six profiles, (2) performing trial-by-trial Bayesian posterior updating for each prototypical profile across the 34 learning trials, and (3) assigning new learners to the best-fitting profile via lowest Wasserstein distance, so yoked children see the responses they would most likely have generated themselves. (Brod et al. (2025))

Claims

-

Key Sources

  • Brod, G., Holstein, E., Weindorf, L., Colantonio, J., Bonawitz, E. & Theobald, M. (2025). Do it yourself: discerning the effects of self-directed activity on conceptual learning. npj Science of Learning. https://doi.org/10.1038/s41539-025-00364-9
Page metadata
Field Value
type research-method
id bayesian-yoking-procedure
title Bayesian Yoking Procedure
description A novel methodological approach in which each yoked participant observes the responses of an "ideal Bayesian learner" personalized to have that participant's individual prior beliefs.
status review
generated by process:settle-candidates on 2026-10-26
trust unverified — no one has confirmed this page's content

Frontmatter is the page's machine-readable record — see the Schema & Guide.