Spss for windows version 25

The characteristics of the patients are shown as counts and proportions. The categorical variables were compared using the chi-squared test or Fisher’s exact test when there were ≤ 5 observations in a cohort. The unpaired Student’s t-test was used to compare quantitative parameters. The relationship between two continuous variables was tested by linear regression analysis. A univariate Cox regression model was used for survival analysis. Using a threshold of P < 0.05 on univariate analysis, variables were then entered in a stepwise Cox regression analysis to identify independent factors, with the criterion for retention of factors in the final model being P = 0.05. Recurrence-free survival (RFS) was defined as the time from surgery to documented clinical recurrence or death, with overall survival (OS) defined as the time from surgery to death. The Kaplan-Meier method was used to prepare survival curves, which were then compared using the log-rank test. Differences with a P value < 0.05 were considered significant. SPSS for Windows Version 25.0 (SPSS, Inc., Chicago, IL, USA).

A statistical analysis was conducted using SPSS for Windows^®, Version 25.0 (Statistical Package for Social Sciences, Chicago, IL, USA). The normality of the distribution was assessed by the Kolmogorov–Smirnov test. The differences between the central tendency values of the two subgroups examined were evaluated by the Mann–Whitney test and Student’s t test. Values are here reported as mean ± standard deviation (SD) and as median and interquartile range (25–75th percentile) for the parametric and non-parametric variables, respectively. The correlations between the variables were evaluated using the Pearson correlation coefficient (r) and Spearman’s rho for the normally distributed and non-normally distributed variables, respectively. Values of p < 0.05 were considered statistically significant. A multiple linear regression analysis model, adjusted by smoke and working age, was applied to assess the association between the biomarkers and workplace exposure.

All data were expressed as the mean ± standard error of mean (SEM). The fusion rates between the right PLIF cage and the left PLIF cage were compared, and they did not follow a normal distribution, so a Mann–Whitney U test was used as a statistical analysis method. Since the comparative analysis of HU values follows a normality distribution, each feature value was analyzed with incremental reduction analysis and an independent samples t-test. The incremental reduction analysis calculated the difference between the mean feature values at follow-up, and the t-test compared the left and right differences. A p-value < 0.05 was considered statistically significant. All statistical analyses were performed using SPSS for Windows version 25.0 (SPSS, Inc., Chicago, IL, USA).

Data management and statistical analysis were performed using SPSS for Windows, version 25.0 (SPSS Inc. Chicago, IL). Differences in proportions were analysed using Chi-square test. Continuous variables were expressed in medians and interquartile ranges (IQR) or range. Correlations were expressed with Pearson or Spearman Correlation Coefficient. Inter- and intra-rater reliability of CTA variables were expressed as intraclass correlation (ICC) with 95% confidence intervals (CI), and a value of > 0.7 was regarded as satisfactory [9 ]. Diagnostic performance of different threshold values for SMA endoprosthesis stenosis using trans-stenotic MAP gradient as reference (≥10 mm Hg) resulted in a receiver operating characteristics (ROC) curve and expressed with area under the curve (AUC) value. The AUC values were interpreted as follows: 0.90–1.0 = excellent; 0.80–0.90 = good; 0.70–0.80 = fair; 0.60–0.70 = poor; 0.50–0.60 = failure. Sensitivity, specificity, positive predictive value, negative predictive value and accuracy were calculated with 95% CI for endoprosthesis stenosis in the SMA ≥ 50% at CTA after cross tabulation against MAP gradient ≥10 mm Hg. A p value < 0.05 was considered significant.

A sample size calculation was conducted with a 95% CI, population proportion of 50%, and a population size of 120, which resulted in a sample size of 92 respondents. The data were evaluated both quantitatively and qualitatively. Quantitative statistical analyses were performed with SPSS for Windows (version 25.0) under the assumption that the variables followed a normal distribution. First, for reliability analysis, the Cronbach α for internal consistency was computed to assess the 6 items in the quantitative part of the questionnaire (ie, Items 1-6). The internal consistency was satisfactory (α=.86), and reliability could not be improved by deleting items [54 (link)]. Corrected item–total correlations for all 6 items ranged between .45 and .81, and mean (SD) values were calculated. The final 4 items addressed in free-text responses (ie, Items 7-10) were evaluated in thematic content analysis using Microsoft Excel as coding software [55 (link)]. Themes in the data set were identified, analyzed, and documented. During content analysis, the reviewers familiarized themselves with the data and developed codes. After themes were sought, examined, and specified, results of the analysis were interpreted.

We assessed the prevalence of blindness, moderate to severe VI, and mild VI (reported as means with 95% CIs) using SPSS for Windows, version 25.0 (SPSS Institute), and we performed a binary regression analysis of the association between the prevalence of moderate to severe VI or blindness and other demographic, clinical, and ocular factors.^{23 (link)} This analysis was followed by a multivariable regression analysis, with the prevalence of blindness or moderate to severe VI as the dependent variable and all factors that were significantly associated with prevalence as independent variables in the univariate analyses. We then removed, in a step-by-step manner, those factors from the list of independent variables that had collinearity with other factors and that were no longer significantly associated with the prevalence of moderate to severe VI or blindness. We calculated the odds ratios (ORs) and their 95% CIs. The significance threshold was 2-sided P < .05.