THE SPEED-ERROR TRADE-OFF PROBLEM IN PSYCHOMETRIC TESTING

The standard procedure for scoring speeded psychometric tests (guessin g corrected number right in fixed time) produces scores which depend b oth on the speed and accuracy of candidates' responding. These in turn depend both on a candidate's ability to perform the task and the comp romise between speed and accuracy which is adopted. This paper uses co mputer simulations based on McClelland's (1979) cascade model to inves tigate the extent to which the scores produced reflect ability, as the y purport to do, and the extent to which they are contaminated by spee d-error strategy. The standard scoring procedure: is compared with som e alternative methods for combining speed and accuracy. It is conclude d (a) that the standard scoring procedures give scores which are: stro ngly affected by the candidate's compromise between speed and error, ( b) that alternative scoring formulae may be less affected and (c) that tests for the sensitivity of scares to speed accuracy compromise shou ld be added to standard test development procedures.