2.10. Statistical Analysis of the Data Obtained in the Clinical Study

The data were tabulated using Microsoft Office Excel^® (Office 2016, Redmond, WA, USA). The quantitative variables of quality of life, disease severity, and skin hydration had their values compared before and after treatment for each patient separately, all of them summarized using mean, standard deviation, median, minimum, and maximum.

The categorical qualitative variables were: gender, schooling, race, marital status, frequencies of consultations with the annual dermatologist, and classification of the disease severity score. The confounding variables were analyzed using absolute and relative frequencies. The association between categorical variables was evaluated using Fisher’s Exact test when there were two categories, and one of them had an n less than 5. The chi-square test per association was used for more than two categories to determine whether both groups were homogeneous regarding possible interferences to treatment. To perform Fisher’s Exact test for confounding variables, they were grouped into two categories: with and without confounding, due to the low n for each. In addition, data in 2 × 2 tables were evaluated by the McNemar test and in 3 × 2 by a Poisson model transformed to ordinal to determine whether the occurrence rate differed for both groups.

The continuous variables were compared using the t-test. A significance level (α) of 5% was set, and statistical analyses were conducted with the MINITAB software, version 17 (Minitab Inc., State College, PA, USA).