An Investigation of the Influence of Internal Test Bias on Regression Slope.

REGRESSION analysis; TEST bias

In educational and psychological tests, 2 forms of bias have been distinguished: internal and external (or predictive) bias. However, the relation between internal and external test bias has not been clearlydefined or explicated. Studies of predictive bias show that when regression equations across groups are compared, the most commonly occurring difference is in intercepts rather than in slopes. Thus, doesinternal test bias not produce slope differences? To answer this question, emphasis was given in this study to an investigation of the relation between internal test bias and slope differences. Monte Carlosimulation results indicate a strong relation between internal test bias and slope differences. However, this relation does not necessarily imply that an absence of internal test bias leads to slope invariance.Conversely, slope differences do not necessarily imply internal test bias. Slope invariance holds only when both target ability differences and test bias do not exist. Finally, we discuss the reasons slopedifferences are rarely observed in practice. [ABSTRACT FROM AUTHOR]

Copyright of Applied Measurement in Education is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)