AUTOCORRELATION OF CHOICE-REACTION TIMES

A choice-reaction (CR) task requires that the subject estimate, raking the warning signal or his response on the preceding trial as a reference point, the time when the reaction stimulus is due, so that he can begin deciding on his response at an appropriate time. This paper presents a model for the reproduction of temporal intervals, with particular emphasis on the sequential statistics of a series of such reproductions. When this model is concatenated with the sequential probability ratio test model for 2CRT, it provides a quantitative account of the pattern of autocorrelation found in a series of RTs. There is no corresponding autocorrelation in the incidence of errors, however, because after an error the subject systematically adjusts the epoch at which he begins sampling as a precaution against a further error. These post-error adjustments can readily be incorporated into the model. The ideas presented enable several different CR phenomena to be related, and they have implications for the relation between speed and accuracy, for the form of empirical distributions of RTs, and for the effects of temporal uncertainty. © 1979.