摘要：Including students with special educational needs in learning (SEN-L) is a challenge for large-scale assessments. In order to draw inferences with respect to students with SEN-L and to compare their scores to students in general education, one needs to assure that the measurement model is reliable and that the same construct is measured for different samples and test forms. In this article, we focus on testing the appropriateness of competence assessments for students with SEN-L. We specifically asked how the reading competence of students with SEN-L may be assessed reliably and comparably. We thoroughly evaluated different testing accommodations for students with SEN-L. The reading competence of N = 433 students with SEN-L was assessed using a standard reading test, a reduced test version, and an easy test version. Also, N = 5,208 general education students and a group of N = 490 low-performing students were tested. Results show that all three reading test versions are suitable for a reliable and comparable measurement of reading competence in students without SEN-L. For students with SEN-L, the accommodated test versions considerably reduced the amount of missing values and resulted in better psychometric properties than the standard test. They did not, however, show satisfactory item fit and measurement invariance. Implications for future research are discussed.
