Balanced bootstrap sampling (METHOD=BALBOOTSTRAP) selects r bootstrap samples of N units, where N is the total number of sampling units (in the stratum or in the data set) and r is the number of samples (replicates) that you specify. Units are selected with equal probability and with replacement. The bootstrap selection is balanced so that the total number of selections (over all replicate samples) is r selections for each sampling unit. For more information, see Davison, Hinkley, and Schechtman (1986). PROC SURVEYSELECT performs balanced bootstrap selection by using the algorithm of Gleason (1988).