Key points are not available for this paper at this time.
An evaluation of the Percentage of Nonoverlapping Data (PND) approach for quantifying outcomes of single-subject research reveals that it is potentially too sensitive to atypical baseline data, not powerful enough to discriminate important treatment differences, and adversely affected by even subtle trends in the data. Suggestions for correcting some of the problems are provided, but the overall recommendation is for additional empirical studies before admitting any such metric into accepted practice.
Owen White (Sun,) studied this question.