2.4. Statistical Analysis

Statistical analysis was performed using R 4.0.3 with the dplyr [57], ggplot2 [58] and arsenal [59] packages. Dplyr was used for data transformation, ggplot2 for data visualization and arsenal for statistical calculations. For numerical variables, t-tests were used, and the Mann–Whitney U-test was used where the data were not normally distributed. Normality was checked with Shapiro–Wilk’s test. For categorical variables, we used the chi square test, and when the expected frequency in a cell was less than 5, we used Fisher’s exact test.

Multivariate linear regression was used to estimate the relationship between fiber and SFA, intake and LDL cholesterol, adjusted for age, sex and smoking. However, only age from these adjustments was statistically significant. The adjusted R² model was used to assess the contribution of dietary fiber in explaining LDL cholesterol. The model was checked for linearity and homoscedasticity. The threshold for statistical significance was p < 0.05. No missing data were present. No sensitivity analysis was performed. Data are presented as the means (standard deviation).