摘要：Collentine (2004) raises the question of whether students experience substantial improvement with respect to grammatical accuracy in a study abroad context or not. In order to answer this question, 98 students of Spanish wrote a composition at the beginning of their study abroad session and three months later, they wrote a second composition, keeping the topic and the instructions constant. The compositions were coded according to 22 grammatical and lexical features of Spanish deemed problematic for first language speakers of English. Variables related to fluency and to less reliance on their L1 turned out significant in compositions written by second year students. Third-year students showed progress mainly in subordination-related aspects of their interlanguage, as well as in the correct choice between preterit and imperfect, and agreement. Advanced students, however, did not show any statistically significant improvement for the variables under scrutiny. This study emphasizes the importance of choosing the appropriate type of assessment tool for each group of students.
