Analyzing the path of responding in maze-solving and other tasks

Abstract

Response time and accuracy are sensitive measures of overall performance but may mask underlying response strategies. For example, analysis of latency and accuracy measures produced in a computerized-maze task does not reveal whether rhesus monkeys really "solve a maze" or simply move as much as is possible toward the target, negotiating barriers through trial and error as they encounter them. Regression procedures are described for analyzing response path against several hypothetical response curves, and analyses of response path for rhesus monkeys' performance on the computerized MAZE task are presented as an illustration. The data suggest that rhesus monkeys do invoke a response strategy of solving the maze, because the observed response topography is significantly associated with the optimal path of responding. Many experimental paradigms should similarly benefit from analysis of the response paths that subjects exhibit.