Pasw statistics for windows

Data analysis was performed using the SPSS software (SPSS Inc. PASW Statistics for Windows, Version 21.0, USA).
Continuous variables are reported as mean and standard deviation (SD) or median and interquartile range. Categorical variables are reported as absolute and relative frequencies. To compare the continuous variables between the groups, the Student's t-test was used. In case of asymmetry, the Mann-Whitney test was applied. For an adjusted calorie-intake combination, the covariance analysis (ANCOVA) was performed.
To control for confounding factors in evaluating the association of nutrients with CAC, a multivariate linear regression model was used. For variables with asymmetric distribution, logarithmic transformation was applied for the utilization of parametric tests.
The statistical significance level considered was 5% (P≤0.05).

At least three replicates were carried out for each measurement. Statistical analyses were performed with t-tests and a one-way analysis of variance (p < 0.05) using PASW Statistics for Windows (Version 18: SPSS, Chicago, IL, USA). Standard deviations were calculated for selected parameters.

The study was approved by the Monash Health Research Ethics Board (approval number RES‐18‐0000‐249Q). The study conformed to the standards set by the latest version of Declaration of Helsinki, except for registration in a database. Standard practice in our Unit is to start captopril in consultation with renal and cardiac physicians after informed discussion with the parents when systolic BP is consistently above 99th centile for PMA (Dionne et al. 2012). Clinical data were retrieved from medical records. Infants were monitored using bedside ECHO (as part of standard management at the institution). All ultrasound recordings were performed using the Vivid 7 and E95 Advantage cardiovascular ultrasound system (GE Medical Systems, Milwaukee, WI, USA). Congenital heart disease and pulmonary vein stenosis were ruled out by ECHO. Offline analysis was performed using EchoPAC™ (Horten, Norway). Standard ECHO indices were measured as described in detail previously (Sehgal et al. 2016a,b,c). Vascular and cardiac function indices were summarized as means ± SD. Data were analyzed using Stata software version 14 (StataCorp, College Station, Tex., USA) and SPSS version 18 (PASW Statistics for Windows; SPSS Inc., Chicago, Ill., USA). Variables were compared using Student's t‐test and statistical significance was regarded as two‐tailed P < 0.05.

At least three replicates were carried out for each measurement. Statistical analyses were performed with t-tests and one-way analysis of variance (p < 0.05), using PASW Statistics for Windows (Version18: SPSS Inc., Endicott, NY, USA). Standard deviations were calculated for selected parameters. The significant differences were established with a confidence level of 95% (p < 0.05), which are indicated with different letters in the different tables.

Since all EBUS-TBNA cases applied for restaging in a particular period were included in this study retrospectively, a power analysis was not performed beforehand. Statistical analyses were conducted using Predictive Analytics Software (PASW) Statistics for Windows (SPSS Inc. Version 18.0, Released 2009; Chicago, IL, USA). The descriptive data were defined as the mean standard deviation or median (minimum–maximum) values for the continuous variables and as percentage values for the categorical variables. The sensitivity, specificity, diagnostic accuracy, and positive and negative predictive values (PPVs, NPVs) were calculated for EBUS-TBNA as follows: sensitivity (True positive (TP)/ [TP + False negative (FN)]), specificity (True negative (TN)/ [TN + False positive (FP)]), PPV (TP/[TP + FP]), NPV (TN/[TN + FN]), and diagnostic accuracy ([TP + TN]/total patients).

The Kolmogorov–Smirnov test was used to determine the distribution of the data. For skewed variables, log-transformations or non-parametric analysis were used as appropriate. Subject characteristics are presented as median, 25^th and 75^th percentiles and the groups were compared by Mann-Whitney U test. H₂O₂ concentration and activity of its metabolizing enzymes were compared in the visceral versus subcutaneous fat compartments by Wilcoxon signed rank test. Associations of interest were evaluated using Spearman or Pearson correlations as appropriate. Multivariate linear regression was used to investigate whether catalase, superoxide dismutase or H₂O₂ were independent predictors of HOMA-IR, after adjustment for age and BMI. Separate models were fitted for each parameter, due to strong collinearity among the predictor variables. PASW Statistics for Windows (20.0; SPSS Inc., Chicago, IL, USA) and GraphPad Prism (version 6.0f for Windows) were used for analysis and presentation of data. All tests were two-tailed and P <0.05 was considered significant.

Descriptive statistics were used to summarise demographic data. Categorical data are presented as numbers and percentages. Continuous data are presented as mean ± standard deviation or median and range. All analyses were performed using PASW Statistics for Windows (version 18.0; SPSS Inc., Chicago, IL, USA). Multivariate analysis was performed using the forward stepwise and multiple logistic regression methods.
Univariate and multivariate logistic regression analysis were used to identify statistically significant independent factors association. Factors having a p-value of less than 0.10 in the univariate analysis were imported to multivariate logistic regression to control the effect of possible confounding factors. Factors were chosen using the forward-stepwise likelihood ratio approach in the multiple logistic regression model, and the adjusted odds ratio (AOR) with its 95% CI at a p-value of ≤ 0.05 was used to determine statistically significant association.