In order to determine the rules of sequencing of songs used by American redstarts, we related Markovian and hierarchical models to recordings obtained from free-living males. In the smaller repertoires of three or four songs, low order Markov chain models fitted the data. 9 of the 10 sequences so examined were first-order, and the last was second-order. Larger repertoires of 6 and 8 songs were hierarchical in organization with subsets of songs having independent sequencing rules. Most samples of singing were stationary in their transition rules over periods of several days: non-stationarity was sometimes associated with a change in the number of songs forming the sequence, or in repetitions of songs. We examine causal models of song sequencing and conclude that our results generally favor competition models, although some sequential dependencies may also apply. Hierarchical organization in the serial repertoires of American redstarts may reflect developmental influences rather than effects of repertoire size itself.