Reliability and validity of a single-item computer science identity instrument

Student identity measures in Science, Technology, Engineering, and Mathematics (STEM) fields are a strong predictor of future persistence in those disciplines. However, there is a paucity of studies with validated measures of students’ computer science (CS) identity. The aim of the present study was to assess the reliability and validity of a proposed single-item CS identity measurement for college students (CS-I-1) that balances practical considerations and psychometric concerns. Using data from 6,044 college students across the United States, we examined the criterion, concurrent, construct validity, as well as the reliability of a CS identity measures. We find that a single item, “I see myself as a computer science person,” (with a 6-point rating scale ranging from 0 = not at all to 5 = very much) is both valid and reliable as a single-item CS identity measure among U.S. college students. Being a quick and easy-to-use diagnostic tool, this measure has both practical utility and theoretical significance. We foresee its simple use in identify students with potential for pursing a CS career and for gauging the impact of CS courses and other experiences when used as a pre- and post-test measure, making it a valuable tool for assessing changes in CS identity among students.