Person and item fit statistics were similar across pilot and comparison groups, with items showing overfitting in both¶
Claim · All claims
Evidence · 1 study (2 entries) · causalr2·q2
Currency · newest study 2023 · not yet checked against its sources · not reviewed by a person · recheck by 2026: tool and model accuracy changes quickly
Subclaims¶
Reading the evidence codes
q is the design tier, i the impact, n the sample, and the kind with its r
the rigour judged within that kind: what each code means.
This claim: no standardized effect is recorded in observations/ for it yet, so no benchmark reading is possible.
q2 i? Mean observed-minus-expected proportions and outfit statistics were close to expected values and very similar between groups for persons and items. → J. Patrick Meyer 2023
q2 i? Item outfit statistics averaged below one in both groups, indicating overfitting; pilot math showed larger variability in observed-minus-expected item differences. → J. Patrick Meyer 2023 (2)
Evidence¶
J. Patrick Meyer 2023¶
J. Patrick Meyer, Ann Hu, Sylvia Li. (2023). Content Proximity Spring 2022 Pilot Study Research Brief. Psychometric Solutions, NWEA. https://www.nwea.org/research/publication/content-proximity-spring-2022-pilot-study-research-report/
q2 · i? · causal · r2
Person-fit analysis of observed versus expected proportion correct (Table 2.6) showed means "very similar for each group and all are close to zero"; person outfit means were near the expected value of one in both subjects.
"The mean values are very similar for each group and all are close to zero. The standard deviations are also quite similar."
J. Patrick Meyer 2023 (2)¶
J. Patrick Meyer, Ann Hu, Sylvia Li. (2023). Content Proximity Spring 2022 Pilot Study Research Brief. Psychometric Solutions, NWEA. https://www.nwea.org/research/publication/content-proximity-spring-2022-pilot-study-research-report/
q2 · i? · causal · r2
Item-fit analysis (Tables 2.8-2.9) found outfit statistics "all below one on average," indicating overfitting, with similar item outfit between groups; pilot math showed larger standard deviations in observed-minus-expected differences.
"As seen with person outfit, the fit statistics in Table 2.9 were all below one on average. Items are also showing overfitting. Item outfit statistics for the two groups are quite similar."
Discussion¶
Related Claims¶
- The Content Proximity spring 2022 pilot study examined validity, reliability, and test score comparability of MAP Growth assessments using the new item-selection algorithm — a broader claim this one bears on
- Growth-norms predictions showed larger RMSDs for pilot math scores but similar predictions for reading — related
- Mathematics items showed more variation in fit statistics than Reading items, and outfit statistics varied more than infit statistics — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
pilot-person-item-fit-similar |
title |
Person and item fit statistics were similar across pilot and comparison groups, with items showing overfitting in both |
description |
Person and item fit statistics were similar across pilot and comparison groups, with items showing overfitting in both |
status |
review |
evidence_strength |
moderate |
newest_evidence |
2023 |
recheck_by |
2026 |
generated |
by process:wiki-ingest on 2026-10-08 |
trust |
unverified — no one has confirmed this page's content |
sources |
2 — j-patrick-meyer-2023, j-patrick-meyer-2023-2 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.