Learning analytics application to examine validity and generalizability of game?based assessment for spatial reasoning

Game-based assessment (GBA), a specific application of games for learning, has been recognized as an alternative form assessment. While there is substantive body literature that supports the educational benefits GBA, limited work investigates validity and generalizability such systems. In this paper, we describe applications learning analytics methods to provide evidence psychometric qualities digital GBA called Shadowspect, particularly what extent Shadowspect robust tool middle school students' spatial reasoning skills. Our findings indicate valid skills, it comparable precision both male female students. addition, enjoyment game positively related their overall competency measured by regardless level existing Practitioner notes What already known about topic: Digital can be powerful context support assess student learning. Games assessments need meet certain generalizability. Learning useful ways establish models games, well investigate qualities. paper adds: How coupled with practices evaluate game-based using techniques. Investigation skills interplay enjoyment. Implications practice and/or policy: incorporate used pencil-and-paper tests measure cognitive reasoning. More training embedded in motivate students who might not on STEM tracks, thus broadening participation STEM. researchers should consider possible factors affect how populations enjoy so does further marginalize populations.