Alexandra Rouquette1, Jean-Benoit Hardouin, Joel Coste. 1. Alexandra Rouquette, Hotel-Dieu Hospital, Biostatistics and Epidemiology Department, 1 place du parvis Notre-Dame, 75181 Paris cedex 04, France, alex.rouquette@gmail.com.
Abstract
OBJECTIVE: To determine the conditions in which the estimation of a difference between groups for a construct evaluated using a composite measurement scale is biased if the presence of Differential Item Functioning (DIF) is not taken into account. METHODS: Datasets were generated using the Partial Credit Model to simulate 642 realistic scenarios. The effect of seven factors on the bias on the estimated difference between groups was evaluated using ANOVA: sample size, true difference between groups, number of items in the scale, proportion of items showing DIF, DIF-size for these items, position of these items location parameters along the latent trait, and uniform/non-uniform DIF. RESULTS: For uniform DIF, only the DIF-size and the proportion of items showing DIF (and their interaction term) had meaningful effects. The effect of non-uniform DIF was negligible. CONCLUSION: The measurement bias resulting from DIF was quantified in various realistic conditions of composite measurement scale use.
OBJECTIVE: To determine the conditions in which the estimation of a difference between groups for a construct evaluated using a composite measurement scale is biased if the presence of Differential Item Functioning (DIF) is not taken into account. METHODS: Datasets were generated using the Partial Credit Model to simulate 642 realistic scenarios. The effect of seven factors on the bias on the estimated difference between groups was evaluated using ANOVA: sample size, true difference between groups, number of items in the scale, proportion of items showing DIF, DIF-size for these items, position of these items location parameters along the latent trait, and uniform/non-uniform DIF. RESULTS: For uniform DIF, only the DIF-size and the proportion of items showing DIF (and their interaction term) had meaningful effects. The effect of non-uniform DIF was negligible. CONCLUSION: The measurement bias resulting from DIF was quantified in various realistic conditions of composite measurement scale use.
Authors: Alexandra Rouquette; Théotime Nadot; Pierre Labitrie; Stephan Van den Broucke; Julien Mancini; Laurent Rigal; Virginie Ringa Journal: PLoS One Date: 2018-12-06 Impact factor: 3.240
Authors: Stéphanie Bourion-Bédès; Raymund Schwan; Vincent Laprevote; Alex Bédès; Jean-Louis Bonnet; Cédric Baumann Journal: Health Qual Life Outcomes Date: 2015-10-24 Impact factor: 3.186