This study aims to validate the STEM career interest survey (STEM-CIS) using Rasch model approach. This study involved 572 junior high school students with 105 seventh-grade students, 124 eighth-grade students, and 343 ninth-grade students. The data were analyzed using Rasch model, which included analysis of item validity and reliability, item fit order, Wright map analysis, and DIF analysis. The results present that the STEM-CIS items show good measurement skills and have logical predictive abilities. STEM-CIS items also have very good reliability, and most items meet the item fit order test criteria. However, there are some items from the STEM-CIS that still detect gender and grade level bias. This study provides evidence that the STEM-CIS items are tested to be valid and reliable to measure students’ interest. In addition, this study also provides evidence that some STEM-CIS items still detect gender and grade level bias.
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.