Measure for Measure: New Developments in Measurement and Item Response Theory

Abstract

For the past 70 years, test development has been dominated by what is called classical test theory (CTT). However, there are many problems associated with CTT, including: the resulting scales tend to be long; their interpretation is highly dependent on the normative sample; the assumption that each item contributes equally to the total score is often wrong, as is calculating a single index of measurement error for all possible scores; and it is difficult to equate different tests developed using CTT. Recently, a new approach to scale development has appeared, called item response theory (IRT), which overcomes all of these problems and, in certain cases, results in a scale with true interval-level properties. This article is an introduction to IRT. It concludes by discussing why IRT hasn't been adopted more widely, and some of its limitations.

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 — 45 citations exist upstream.

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