Unidimensional Rasch model scaling

Research Method · All research methods
Evidence · 7 claims (4 for, 3 mixed) · 5 studies (3 associational, 2 design), q2 · 0 of 5 report an effect size · 7 claims rest on one study

Description

All MAP tests assume a single latent achievement factor and are scaled on the unidimensional Rasch model with the RIT scale, linearly transformed from logits (RIT = logit x 10 + 200). The article's stated rationale is that "Rasch model has unique properties over other models", including sufficiency, separability, specific objectivity, and latent additivity, and that the model preserves the interpretability of the construct map and item order across the person-location range.

Accounts

• Unidimensional Rasch model scaling of MAP scores on the RIT scale: All MAP tests assume a single latent achievement factor and are scaled on the unidimensional Rasch model with the RIT scale, linearly transformed from logits (RIT = logit x 10 + 200). The article's stated rationale is that "Rasch model has unique properties over other models", including sufficiency, separability, specific objectivity, and latent additivity, and that the model preserves the interpretability of the construct map and item order across the person-location range. (Shudong Wang et al. (2013))

Claims

• A one-factor unidimensional model is the most reasonable fit for MAP computerized adaptive Reading and Mathematics tests across grades, terms, and ten states, though Michigan Mathematics misses the RMSEA criterion [+M]
• Item calibration results from Pychometrik and the existing tool are mostly comparable across 1,180 AGC-calibrated MAP Growth items, with average RIT differences ranging from 0.33 (mathematics) to 0.91 (science) [+W]
• Average on-grade and all-grade item difficulty estimates differ by less than 0.1 logit for MAP Growth items [+W]
• Rescoring with new item parameters changed average ability estimates negligibly, with new and original scores correlated above 0.99 [+W]
• For items aligned to multiple target grades, difficulty estimates from different on-grade calibration samples differ negligibly, at most 0.1 logit on average [~W]
• Item difficulty estimates from target-plus-adjacent-grade samples generally differ from original estimates about as much as on-grade estimates do, with mean differences within 0.11 logit [~W]
• Point measure correlations were unchanged by the difficulty adjustment because the new person ability estimates are linear transformations of the old ones [~W]

Related Research Methods

-

Key Sources

• Shudong Wang, Marty McCall, Hong Jiao, & Gregg Harris. (2013). Construct Validity and Measurement Invariance of Computerized Adaptive Testing: Application to Measures of Academic Progress (MAP) Using Confirmatory Factor Analysis. Journal of Educational and Developmental Psychology, 3(1). https://doi.org/10.5539/jedp.v3n1p88

Page metadata

Field	Value
type	research-method
id	unidimensional-rasch-model-scaling
title	Unidimensional Rasch model scaling
description	All MAP tests assume a single latent achievement factor and are scaled on the unidimensional Rasch model with the RIT scale, linearly transformed from logits (RIT = logit x 10 + 200).
status	review
moved_from	theory/rasch-unidimensional-scaling-rit-map
generated	by process:sweep-kinds on 2026-10-10
trust	unverified — no one has confirmed this page's content
sources	1 — shudong-wang-2013

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