Spss ver 26.0 for windows

Initially, univariate analyses with the t-test and the chi-squared test were used to evaluate the differences in age, sex (binary), body mass index (BMI), current smoking history, number of teeth, ABL (three groups), and hs-CRP value (three groups) and between subjects with and without type 2 diabetes. Next, multivariate logistic regression analysis was undertaken with forward selection adjusting for age, sex (binary), BMI, current smoking history (binary), number of teeth, and the nine classifications of periodontal disease severity. Receiver operating characteristic (ROC) curve analysis was employed to identify asymptomatic type 2 diabetes in relation to ABL and hs-CRP value. According to the method suggested by Swets [18 (link)], the area under the ROC curve (AUROC) was determined as follows: less accurate (0.5 < AUROC < 0.7), moderately accurate (0.7 < AUROC < 0.9), highly accurate (0.9 < AUROC < 1), and perfect tests (AUROC = 1). All comparisons were two-sided and performed at a p = 0.05 level of significance. Statistical analysis was performed using SPSS^® ver. 26.0 for Windows (IBM Japan, Tokyo, Japan).

Statistical analysis was performed using the 1-sample Kolmogorov-Smirnov test to examine whether the factual score and conceptual score followed a normal distribution. We reported the median and interquartile range (IQR), as the score distribution was not normal. We used the independent-samples Kruskal-Wallis test to compare the score distribution among the study groups. We considered a P-value less than 0.05 to be statistically significant. We used IBM SPSS ver. 26.0 for Windows (IBM Corp., Armonk, NY, USA) for data analysis.