Sleep staging has been conventionally performed using neurophysiologic and behavioral criteria. However, these criteria may not always be available. Since it is known that cardiorespiratory variables in rapid eye movement (REM) sleep are different from those in quiet sleep, we asked whether such variables can be used for the determination of sleep state. We studied nine normal fullterm infants at 1 and 4 months of life. Ventilation was measured using barometric plethysmography and the RR interval using a high accuracy R wave detector. Electroencephalogram, electrooculogram, and postural muscle electromyogram were recorded using surface electrodes and behavioral criteria applied. Means of RR interval, respiratory cycle time and tidal volume, and coefficients of variation of the same variables, were obtained for 30-s intervals throughout each sleep study. The Kolmogorov- Smirnov distances between REM and quiet sleep were larger for the coefficients of variation than for the means at both ages for all variables. Moreover, coefficient of variation of respiratory cycle time was found to provide the largest separation between REM and quiet sleep. In view of this result, we developed a statistical decision rule using coefficient of variation of respiratory cycle time for the classification of REM and quiet sleep in blocks of 5-min periods. Each study was divided into 5-min epochs and this rule was applied to each epoch. Of 85 epochs staged as quiet sleep by neurophysiologic and behavioral criteria, 79 epochs (or 93%) were classified correctly as quiet sleep using our decision rule. Of 85 epochs staged as REM sleep, 84 were classified as REM sleep and only one misclassified as quiet sleep. Five additional infants, whose results did not enter into the formulation of the decision rule, were used as a subsequent example to test the rule. The results of these five infants were similar to those of the previous nine others. We conclude that in young infants 1) the variability of cardiorespiratory parameters can separate quiet from nonquiet sleep better than the mean values and 2) sleep staging using a decision rule based on coefficient of variation of respiratory cycle time can be performed with high degree of accuracy.