2.8. Sample size and Statistical analysis
We could not calculate the sample size from any previous study, since
there was no study conducted with similar methodology. Therefore, We
used a power of 0.90 and significance level of 0.05 to calculate a
sample size of 18 patients for three groups when compared with ANOVA.
Considering the dropouts, we determined the number of patients as 20 in
each group.
Statistical Package for the Social Sciences version 16.0 statistical
package program (SPSS Inc., Chicago, IL, USA) was used for statistical
analysis. Descriptive statistics were expressed as mean ± SD. The
univariate analysis compared in groups means using a two-sample,
independent t -test assuming equal variances for continuous
variables. For data without normal distribution, Mann–Whitney U-test
was performed. Ratios were compared using the Chi-Square test.
Categorical variables were compared using the Fisher’s exact test.
Continuous variables were tested for normality via the Shapiro–Wilk
test. One-way ANOVA test was used to compare the mean of the groups, and
the post-hoc Tukey test was used to determine where the difference
between groups originated. Bonferroni correction was used because there
are 7 different frames in NRS evaluations. Statistical significance was
accepted as p <0.05 except for NRS evaluations, and p
<0.007 in NRS.