Detection of aberrant test-taker responses is an important component of test security. According to the current research literature, there are five major causes of aberrant responses: answer copying, creative responding, careless responding, lucky guessing, and random responding. From a test security perspective, answer copying is the primary consideration when it comes to paper-and-pencil tests. Answer-copying behavior often results in an unusual agreement between the incorrect answers for a pair of test takers.
A common approach to detecting unusual agreement between the incorrect answers of two test takers is the K-Index probability. The K-Index has been used at the Educational Testing Service (ETS) for decades, and its properties have been further explored in the literature. The major disadvantage of the K-Index is a high Type II (i.e., false-negative) error rate. This paper presents a new approach called the M-Index. A computational study comparing the K-Index with the M-Index demonstrates that the M-Index has a lower Type II error rate and a Type I (i.e., false-positive) error rate below the nominal level.
Request the Full Report
To request the full report, please email Linda Reustle at lreustle@LSAC.org.