摘要：The mode of administration effects reported here and in previous studies (Russell, 1999; Russell and Haney, 1997) highlight a complicated challenge testing programs must overcome as they continue to use tests containing open-ended items to make inferences about student and school achievement. To reduce the mode of administration effect, state testing programs should consider allowing students to select the mode by which open-ended responses are composed. For the past decade, the Province of Alberta has employed this strategy for its graduation testing program (Alberta Learning, 2000). Over the past five years, the province has seen the percentage of students opting to perform the English, Social Studies, Biology and French tests on computer increase from 6.7% in 1996 to 24.5% in 2000. Within high schools, the percentage of students opting to perform the test on a computer ranges from 0 to 80% (Sakyi, 2000).
