“…Frequently, the use of more than one statistical test may be necessary in a single research project, due to the different hypotheses being tested. This is the case of the RCT conducted by Muller et al 11 , which investigated the effects of an intervention to improve patients' knowledge of skin lesions suspected of being melanoma. Different tests may also be combined to analyze independent and paired data, as can be seen in the study by Bagatin et al 4 In such cases, a thorough consideration of which tests should be used to test not only the primary association of interest, but also secondary associations, is essential.…”