Concordance Between ACT and ITED Scores From Different Populations

Abstract

The use of educational tests in practical situations often requires that tests that are built to different content and/or statistical specifications be statistically linked. When equating methods are applied to tests that differ in content, difficulty, and/or reliability, the resulting scores cannot be used interchangeably. This study examined group invariance under concordance conditions between ACT and the Iowa Tests of Educational Development (ITED) scores. Linear, parallel-linear, and equipercentile methods were used to transform scores on ITED tests to the scale of scores on similarly named ACT tests. Results indicated that when content specifications and statistical properties between the two forms were similar, transformed scores obtained from subgroups and the entire population were similar using the linear or parallel-linear method; otherwise, the linking relationships were group dependent, with the results for the equipercentile method being less group dependent than those for the linear method.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 27 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.