Skip to main content

ORIGINAL RESEARCH article

Front. Educ.
Sec. Assessment, Testing and Applied Measurement
Volume 9 - 2024 | doi: 10.3389/feduc.2024.1248770
This article is part of the Research Topic Insights in Assessment, Testing, and Applied Measurement: 2022 View all 20 articles

Note on the radical inflation in the estimates of error variance

Provisionally accepted
Jari Metsämuuronen Jari Metsämuuronen 1,2*
  • 1 Finnish Education Evaluation Centre (FINEEC), Helsinki, Finland
  • 2 University of Turku, Turku, Southwest Finland, Finland

The final, formatted version of the article will be published soon.

    This note discusses a radical technical inflation in error variance and related standard error related to the test score from the conceptual and empirical viewpoint. The technical inflation is a strict consequent of technical underestimation of item-score correlation by product-moment coefficient of correlation (PMC) embedded in the traditional estimators of reliability such as coefficients alpha, theta, omega, or rho (maximal reliability). Specifically, in the educational settings where the compilation usually embeds both easy and difficult items, the estimate by PMC may be far off the true association between an item and the score. Then, by using the traditional estimators of reliability in the process, the estimates of standard errors are technically inflated because the error variance related to the traditional measurement models is radically inflated and, consequently, the estimates of reliability are radically deflated. Within the educational testing settings, deflation-corrected standard errors using deflation-corrected estimators of reliability in the process would draw us nearer the true accuracy of the test score.

    Keywords: item-score correlation, error variance, Standard errors, Deflation-corrected error variance, Deflation-corrected standard errors

    Received: 27 Jun 2023; Accepted: 09 May 2024.

    Copyright: © 2024 Metsämuuronen. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence: Jari Metsämuuronen, Finnish Education Evaluation Centre (FINEEC), Helsinki, Finland

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.