⁴  For this simulation study, statistical power is defined as the proportion of simulations in which the proposed data permutation method determined the existence of meaningful slope variation when data was generated from a model that included a variable slope. Similarly, specificity is defined as the proportion of simulations in which the proposed data permutation method was unable to determine the existence of meaningful slope variation when data was generated from a model that did not include a variable slope. Type-I and type-II error rates are defined as the proportion of simulations in which the proposed data permutation method detected the existence of meaningful slope variation when data was generated from a model that did not include a variable slope, and the proportion of simulations in which the proposed data permutation method was unable to determine the existence of meaningful slope variation when data was generated from a model that included a variable slope, respectively.