Detecting Biased Items When Developing a Scale: A Quantitative Method

Jean-Charles Pillet, Claudio Vitari (), Federico Pigni and Kevin Carillo
Additional contact information
Jean-Charles Pillet: ESC Grenoble - Ecole Supérieure de Commerce de Grenoble - EESC-GEM Grenoble Ecole de Management
Claudio Vitari: AMU - Aix Marseille Université
Federico Pigni: CETIC asbl - Centre d’Excellence en Technologies de l’Information et de la Communication

Post-Print from HAL

Abstract: In survey research, it is well known that the quality of responses is significantly altered by apparently trivial variations in the linguistic or grammatical properties of survey items. Yet numerous seemingly minor changes are made to survey items in the course of the scale development process so that they comply with other requirements (e.g., content validity). As a result, researchers may inadvertently introduce systematic measurement error that is not accounted for in the final model. Remedies to this problem are widely known, but reliable methods to diagnose it do not readily exist. In an effort to address this shortcoming, we develop a quantitative method to detect biased items and reinforce the reliability of IS measurement instruments. In this paper, we provide step by step implementation guidelines and show how to apply the method and interpret the output results.

Date: 2018
New Economics Papers: this item is included in nep-bec
Note: View the original document on HAL open archive server: https://shs.hal.science/halshs-01923612
References: View references in EconPapers View complete reference list from CitEc
Citations:

Published in AMCIS 2018 Proceedings, 2018, Nouvelle-Orléans, United States

Downloads: (external link)
https://shs.hal.science/halshs-01923612/document (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:hal:journl:halshs-01923612

Access Statistics for this paper

More papers in Post-Print from HAL
Bibliographic data for series maintained by CCSD ().