Spss version 15.0 statistical software

Data were double entered using SPSS version 15.0 statistical software (SPSS Inc. Chicago, 2007) and exported to Stata 12 (Statacorp, USA). Descriptive analyses were done to depict the TBLN presumptive cases’ characteristics. Sensitivity and specificity of the different diagnostic methods (FNA cytology, AFB microscopy, culture on LJ, & BACTEC MGIT 960) were calculated using composite bacteriological methods as reference standard.

Standard descriptive statistics were used to summarize patients' characteristics. Median values and ranges were used for continuous variables, while percentages were computed for categorical variables. Proportions were compared by Pearson's chi-square test or Fisher's exact test, depending on the size and number of the groups compared. Survival analyses were performed according to the Kaplan-Meier method and differences between curves tested by log-rank. Survival curves were truncated at 60 months, since the number of patients remaining at risk was too small afterward. Univariate Cox regression analysis was used to estimate hazard ratio (HR) and 95% confidence intervals (95%CI) for PFS and OS. A p value ≤ 0.05 was retained as the limit of statistical significance. The SPSS version 15.0 statistical software was used to perform all the analyses.

A descriptive statistical analysis will be performed for all study variables. We will calculate the means, medians and standard deviations for quantitative variables and the absolute and relative frequencies for qualitative variables. The 95 % confidence interval will be applied. The analysis will be done according to the intention-to-treat principle. The baseline comparison will be made between the main variables that we expect to be related to the primary outcome using the χ² test or analysis of variance (ANOVA).
At the first level, the between-group comparison for the primary outcome will be explored using the χ² test. Relative risk reduction, absolute risk reduction and NNT will be calculated. Inferences for secondary outcomes will be made using ANOVA or the χ² test.
Finally, a logistic regression model will be used for the primary outcome (performance of the right inhalation technique [yes or no]), considering the intervention as the predictive variable and the rest of the independent measures as the possible modifying factors. We will use the usual 5 % significance level (α = 0.05) and the SPSS version 15.0 statistical software package (SPSS, Chicago, IL, USA) to run the proposed analysis.

Descriptive analysis was carried out using mean ± standard deviation or median and interquartile range (IQR) for the quantitative variables and percentages values for the qualitative ones.
Normality distribution was assessed by the Shapiro-Wilk test. Survival analysis was performed by applying the Kaplan-Meier estimator and Log-rank test for equality of survivor functions. The association with clinical features was analyzed with univariate Cox model of proportional hazards (Hazard Ratio - HR and 95% CI) for OS, and the applicability assumption was evaluated by the Schoenfeld test. A p value ≤ 0.05 was retained as the limit of statistical significance. The SPSS version 15.0 statistical software was used to perform all the analyses.