Single-case comparative studies could help identify efficient instructional procedures for individuals with disabilities. However, previous literature reported inconsistent efficiency results if multiple comparisons were conducted, indicating that within-participant replication was uncommon. In this review, we examined single-case comparative studies with multiple within-participant comparisons and identified the arrangements that may be related to within-participant replication. We performed a multilevel mixed-effects logistic regression analysis to assess the association between different arrangements and consistent efficiency results between the comparisons. We found that some arrangements, such as random assignment of targets and a combination of random assignment and equating procedure, appear more predictive of within-participant replication.