Skip to content

Nonlinear mixed-effects Bayesian learning-curve modeling

Research Method · All research methods
Evidence · 1 claim (1 for) · 1 study (1 associational), q3 · 0 of 1 report an effect size · 1 claim rests on one study

Description

A fully disaggregated nonlinear Bayesian mixed-effects model, implemented in the R package brms, estimating each participant's initial accuracy, rate of change (a time constant), and asymptotic accuracy as a continuous function of trial number, with an exponential change curve bounded via logistic-regression link functions. Fixed effects of task order and feedback were included and found not reliable on their own. The authors state it "prevents the conflation of components of learning inherent in many other forms of learning estimates".

Accounts

  • Nonlinear mixed-effects Bayesian regression model of WM trajectory components: A fully disaggregated nonlinear Bayesian mixed-effects model, implemented in the R package brms, estimating each participant's initial accuracy, rate of change (a time constant), and asymptotic accuracy as a continuous function of trial number, with an exponential change curve bounded via logistic-regression link functions. Fixed effects of task order and feedback were included and found not reliable on their own. The authors state it "prevents the conflation of components of learning inherent in many other forms of learning estimates". (Aaron Cochrane et al. (2021))

Claims

-

Key Sources

  • Aaron Cochrane and C. Shawn Green. (2021). Trajectories of performance change indicate multiple dissociable links between working memory and fluid intelligence. npj Science of Learning. https://doi.org/10.1038/s41539-021-00111-w
Page metadata
Field Value
type research-method
id nonlinear-mixed-effects-bayesian-learning-curve-modeling
title Nonlinear mixed-effects Bayesian learning-curve modeling
description A fully disaggregated nonlinear Bayesian mixed-effects model, implemented in the R package brms, estimating each participant's initial accuracy, rate of change (a time constant), and asymptotic accuracy as a continuous function of trial number, with an exponential change curve bounded via logistic-r
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.