Jackknife leave-one-year-out empirical Bayes estimation of teacher grade effects¶
Research Method · All research methods
Evidence · 4 claims (4 for) · 1 study (1 associational),q3· 0 of 1 report an effect size · 4 claims rest on one study
Description¶
A two-step value-added estimation procedure, adapted from the teacher value-added literature, that produces teacher grade effects used to predict student outcomes. A teacher's grade effect in a given year is estimated from grades given in every other year, so effects 'are not estimated with the same group of students with which we measure student outcomes,' ensuring the measure reflects a teacher characteristic rather than a single year's class conditions.
Accounts¶
- Jackknife leave-one-year-out empirical Bayes estimation of teacher grade effects: A two-step value-added estimation procedure, adapted from the teacher value-added literature, that produces teacher grade effects used to predict student outcomes. A teacher's grade effect in a given year is estimated from grades given in every other year, so effects 'are not estimated with the same group of students with which we measure student outcomes,' ensuring the measure reflects a teacher characteristic rather than a single year's class conditions. (McKenzie et al. (2025))
Claims¶
- Teachers' persistent grade effects predict students' long-term outcomes [+M]
- Teacher grade effects show spillovers to students' broader ninth-grade outcomes [+M]
- Ninth-grade teachers' grade effects are stable across years [+M]
- Ninth-grade teachers vary substantially and systematically in the grades they give [+M]
Related Research Methods¶
-
Key Sources¶
- McKenzie, R. & Allensworth, E. (2025). Variability in the Grades Teachers Give: Teacher Grade Value-Add, Mismatch, and Long-Term Effects. American Educational Research Journal. https://doi.org/10.3102/00028312251345094
Page metadata
| Field | Value |
|---|---|
type |
research-method |
id |
jackknife-leave-one-year-out-empirical-bayes-estimation-of-teacher-grade-effects |
title |
Jackknife leave-one-year-out empirical Bayes estimation of teacher grade effects |
description |
A two-step value-added estimation procedure, adapted from the teacher value-added literature, that produces teacher grade effects used to predict student outcomes. |
status |
review |
moved_from |
element/jackknife-leave-one-year-out-grade-effect-estimation |
generated |
by process:sweep-kinds on 2026-10-10 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — mckenzie-2025 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.