Validation of the Mental Retardation Attitude Inventory-Revised (MRAI-R): A multidimensional Rasch analysis

The purpose of this study is to examine the psychometric properties of the Mental Retardation Attitude Inventory-Revised (MRAI-R) via a multidimensional random coefficients multinomial logit model (MRCMLM) under the Rasch analysis. A total of 521 college students (294 males; 227 females), aged 18-25, in the area of south-east China, completed the MRAI-R (Chinese version). The results showed that the partial credit model had a better goodness of fit than the rating scale model. Among all 29 items, two of them exhibited gender differences (item 2 and 8), and two disordered in their step analyses (item 2 and 22). With the identified four subconstructs, the subscale Subtle Derogatory Beliefs (SUDB) had a relatively low reliability (0.496) while compared to the other three subscales (0.664-0.833). The current results revealed the statistical feasibility of MRAI-R through item calibration. Further work on investigating the details of the item nature itself is recommended. Copyright © 2016 International Journal of Social Science and Humanity. All rights reserved.