ERIC Number: ED409364
Record Type: Non-Journal
Publication Date: 1997-Mar
Reference Count: N/A
Assessing Subgroup Differences in Item Response Times.
Schnipke, Deborah L.; Pashley, Peter J.
Differences in test performance on time-limited tests may be due in part to differential response-time rates between subgroups, rather than real differences in the knowledge, skills, or developed abilities of interest. With computer-administered tests, response times are available and may be used to address this issue. This study investigates procedures for identifying possible subgroup differences in response times from a computer-administered test. Based on the results, it appears that survival analysis methodology is useful for uncovering subgroup differences in response time rates. Data from a national high-stakes computer-administered (but not adaptive) reasoning test were used. Data from 6,306 test takers who said that English was their best language and 462 test takers who said that English was not their best language were analyzed with parametric (Cox regression) and nonparametric (Wilcoxon test) approaches. Significant differences between response times across the two subgroups were found, although this does not necessarily imply that particular items should have been identified as having differential item functioning. (Contains 3 tables, 3 figures, and 11 references.) (Author/SLD)
Publication Type: Reports - Evaluative; Speeches/Meeting Papers
Education Level: N/A
Authoring Institution: N/A