than the power with J=5, indicating that while there is a benefit to statistical power with a certain number of repeated observations, there is a diminishing impact on power as the number of repeats increases. Further, the increase in power is greater when the correlation is lower; e.g., ρ=0.3 versus ρ=0.6. This is as expected since the level of correlation is inversely related to effective sample size. Intuitively, when the correlation between repeated observations is low having additional repeats should provide substantial new information, whereas having a high correlation implies that the repeated observations are not greatly independent of one another and therefore the repeats provide limited additional information. If the correlation is unknown a conservative estimate should be used to calculate power/sample size.
