Stata 14 for windows

We performed statistical analysis with STATA 14 for Windows (StataCorp, College Station, TX). A p-value less than 0.05 was considered statistically significant.

For kappa statistics score-groups 0 and 1 were merged into a “not accepted group” and score-groups 2 or 3 were merged into an “accepted group”. All accepted images received 1 point and not accepted images received 0 point. This allowed us to calculate the intra- and inter-observer reproducibility by means of ordinary Kappa for binomial variables. Inter-observer reproducibility was analyzed using results from the first (baseline) evaluations. The ratings from each observer were cross-tabulated in Epidata Entry Client and agreement was measured using Cohens Kappa statistics in Stata. Results were expressed as Kappa values with standard errors and Z-scores indicated.
A Kappa value of 1 represents perfect agreement between the observers; whereas a value of 0 means that the results were obtained by chance. The Kappa values were interpreted according to the recommendations of Landis and Koch [10 (link)]. Values below 0.00 indicate poor agreement; 0.00–0.20 slight agreement; 0.21–0.40 fair agreement; 0.41–0.60 moderate agreement; 0.61–0.80 substantial agreement and a Kappa above 0.81 indicated almost perfect agreement. Kappa values over 0.6 are considered reliable.
Statistical analysis was performed using the STATA 14 for Windows, Stata Corporation, USA [11 ]; Microsoft Excel 2010, Microsoft Office Package, Microsoft Corporation, USA [12 ]; Epidata Entry Client and Epidata Manager [8 ].

Statistical analyses were performed using Stata 14 for Windows (Stata Corp LP, USA) and Graphpad Prism 6 for Mac (GraphPad Software Inc., USA). Normally-distributed quantitative variables were expressed as the mean ± standard deviation, and non-normally-distributed variables were expressed as the median and interquartile range (IQR). In case of normal distribution, bivariate analyses were performed using a t-test; Mann-Whitney U, Kruskal-Wallis or p-trend tests were used for non-normally distributed variables. The χ² test was used for qualitative variables.

Values were expressed as mean and SD for continuous variables or absolute frequency and percentages for categorical variables. Continuous variables were compared with parametric (Student’s t-test). One-way analysis of variance was used to testify an association between the scores of the questionnaire and the detected anamnestic data. All statistical analyses were carried out using STATA14 for Windows software with a two tailed P value of 0.05 used as a threshold for significance.

Proportions were computed with 95% confidence intervals and continuous variables were described with means and interquartile ranges (IQR). We used Student's T test to compare quantitative variables and Chi² test for qualitative variables. To investigate the association between wheezing and helminth infection status, taking into account air pollution, several regression models were used. We performed a logistic regression with the variable «current wheezing» treated dichotomously (yes/no). A multinomial (polytomous) logistic regression was done with the dependent variable ‘wheezing severity’, a qualitative ordinal variable with three categories (no wheezing/wheezing/severe wheezing). At each of the previous stages, univariate and multivariate analyses were performed. Variables whose p value was < 0.2 at the univariate stage were included in the multivariate model. In this last step the significance level was 0.05. The final model with all significant p values was obtained by eliminating variables through a step-by-step descending method. Effect sizes are presented with 95% confidence intervals. All analyses were performed with Stata 14 for Windows (Stata Corp., College Station, TX).