Exploring the statistical equivalence of the English and Xhosa versions of the Woodcock-Munõz Language Survey

This study explored statistical equivalence of the adapted Xhosa and English version of the Woodcock-Muñoz Language Survey (WMLS) by investigating group differences on each subscale, in terms of mean scores, index reliability, and item characteristics for two language groups. A Convenience quota sampling technique was used to select 188 Xhosa (n = 188) and 198 English (n = 198) learners from Grades 6 and 7 living in rural and urban Eastern Cape. The WMLS Xhosa and English versions were administered to learners in their first languages. Significant mean group differences were found, but differences were not found on the reliability indices, or mean item characteristics. This pointed in the direction of statistical equivalence. However, scrutiny of the item characteristics of the individual items per subscale indicated possible problems at an item level that need to be investigated further with differential functioning analyses. Thus, stringent DIF analyses were suggested for future research on DIF items before the versions of the WMLS can be considered as equivalen