Sas system for windows software

Descriptive analysis was performed, with presentation of frequency tables for categorical variables and position and dispersion measurements for numerical variables. To compare proportions, the chi-square test was used, or Fisher’s exact test when necessary. To compare continuous measurements between two evaluation times, the Mann-Whitney test was used. For comparison between three or more evaluation times, the Kruskal-Wallis test was used, with Tukey’s post-test analysis when significant. For analysis of correlations between continuous variables, linear regression models were used. To assess the reliability of each score at baseline, diagnostic accuracy measurements (sensitivity, specificity, positive and negative predictive values and overall accuracy) were calculated considering histopathological examination as the gold-standard diagnostic method. The significance level adopted for the statistical tests was 5% (P < 0.05). The SAS System for Windows software (Statistical Analysis System), version 9.2, was used (SAS Institute Inc., 2002-2008; Cary, North Carolina, United States).

All statistical analyses were performed by using SAS System for Windows software (Version 9.4; SAS Institute). Count and proportion were used to present categorical variables, while mean with standard deviation and median with minimum and maximum were used for presenting continuous and ordinal data, respectively. Univariable logistic regression analysis was used to determine whether concomitant LM injury, repaired, resected, or left in situ during primary ACLR, affects the ACL revision rate and cartilaginous as well as meniscal status at the time of revision ACLR. Results from the univariable logistic regression analyses were presented as odds ratio, 95% CI, and P value. The area under the receiver operating characteristic curve (AUC) with 95% CI was further calculated. The AUC varies between 0.5 and 1.00, where a higher number represents a better predictive capacity of the statistical model. For instance, an AUC between 0.5 and 0.7 indicates poor predictive capacity of the statistical model, while an AUC between 0.9 and 1.00 represents excellent predictive capacity. All significance tests were conducted at the 5% significance level.

The data were analyzed in the SAS System for Windowssoftware (SAS, 2000). The applicative Guided Data Analysis was used to test the data for residue normality (normal distribution) and homogeneity of variances. If normality was not observed, variables were transformed into their logarithmic or square root values. If after transformation normality was not observed, a non-parametric analysis was carried out using theNPAR1WAY procedure. For data with normal distribution, the ANOVA test followed bya Least Significant Differences (LSD) post-hoc test was used to compare the groups. An α of 5% was considered for all the analyses.