Statistical Methods for Analyzing Attached Gingival Width: A Study Using R and SPSS

Shapiro-Wilk was used to perform normality tests. For non-normally distributed metric data, median [M(QR)] was used to represent the data, while normally distributed metric data was represented in its original form. Chi-square tests were used to compare categorical variables, and Wilcoxon signed-rank tests were used to analyze pre- and postoperative data for the same patient. Mann-Whitney U non-parametric tests were used to compare inter-group differences in attached gingival width, and a generalized additive mixed model was used to compare the attached gingival width at different time points after surgery with the baseline immediately after surgery. The linear regression model was used to compare the inter-group differences in the contraction rate of the attached gingiva, which was calculated as a percentage based on the attached gingival width immediately after surgery, and the correlation was corrected using a generalized estimating equation. The above statistical analysis was performed using R software (http://www.R-project.org) and SPSS 22.0 statistical software.