TY - JOUR T1 - Assessing Individual-Level Impact of Interruptions During Online Testing JF - Journal of Educational Measurement Y1 - 2015 A1 - Sinharay, Sandip A1 - Wan, Ping A1 - Choi, Seung W. A1 - Kim, Dong-In AB - With an increase in the number of online tests, the number of interruptions during testing due to unexpected technical issues seems to be on the rise. For example, interruptions occurred during several recent state tests. When interruptions occur, it is important to determine the extent of their impact on the examinees' scores. Researchers such as Hill and Sinharay et al. examined the impact of interruptions at an aggregate level. However, there is a lack of research on the assessment of impact of interruptions at an individual level. We attempt to fill that void. We suggest four methodological approaches, primarily based on statistical hypothesis testing, linear regression, and item response theory, which can provide evidence on the individual-level impact of interruptions. We perform a realistic simulation study to compare the Type I error rate and power of the suggested approaches. We then apply the approaches to data from the 2013 Indiana Statewide Testing for Educational Progress-Plus (ISTEP+) test that experienced interruptions. VL - 52 UR - http://dx.doi.org/10.1111/jedm.12064 ER - TY - JOUR T1 - Determining the Overall Impact of Interruptions During Online Testing JF - Journal of Educational Measurement Y1 - 2014 A1 - Sinharay, Sandip A1 - Wan, Ping A1 - Whitaker, Mike A1 - Kim, Dong-In A1 - Zhang, Litong A1 - Choi, Seung W. AB -

With an increase in the number of online tests, interruptions during testing due to unexpected technical issues seem unavoidable. For example, interruptions occurred during several recent state tests. When interruptions occur, it is important to determine the extent of their impact on the examinees’ scores. There is a lack of research on this topic due to the novelty of the problem. This article is an attempt to fill that void. Several methods, primarily based on propensity score matching, linear regression, and item response theory, were suggested to determine the overall impact of the interruptions on the examinees’ scores. A realistic simulation study shows that the suggested methods have satisfactory Type I error rate and power. Then the methods were applied to data from the Indiana Statewide Testing for Educational Progress-Plus (ISTEP+) test that experienced interruptions in 2013. The results indicate that the interruptions did not have a significant overall impact on the student scores for the ISTEP+ test.

VL - 51 UR - http://dx.doi.org/10.1111/jedm.12052 ER -