Hi can someone please explain in detail what is meant by the highlighted part here. Are they talking about power calculated by using the parametric or non parametric method? Thanks comments are in order. First and foremost. we have to assume that the underlying distribution is normal to justify using the normal theory test. No such assumption is necessary for the sign test. If the distribution is not normal and the sample size N is large, the calculated power is' an approximation to the power of the normal theory test, by the central limit theorem. However, for the sign test, the size and the power calculations are exact for all sample sizes and no distribution assumptions are needed other than continuity. Further, the normal theory test is affected by the