Sas software package version 9

The TAG and LIMA+SVG groups were compared using Chi-square or Fisher’s exact tests for categorical variables, two-tailed t-tests for continuous variables that were normally distributed, and Wilcoxon rank sum tests for continuous variables that did not have a normal distribution.
One of the primary objectives was > 20% recruitment of patients into the randomized trial. Patient eligibility was based on inclusion and exclusion criteria and assignment to participating surgeons. This allowed for the creation of a predictive model capable to identify factors that predicted use of TAG. Design variables were created for reference level coding of categorical variables with more than two levels. For the multivariable analysis, candidate variables were selected based on clinical relevance or a significance of bivariate association with p value <0.2. A non-parsimonious logistic regression model was developed to identify the predictors of receiving TAG. The area under the receiver operating characteristic (ROC) curve was used to assess predictive accuracy of the model. A bootstrap procedure was used to obtain 1000 subsamples with replacement. The 2.5th and 97.5th percentiles of the bootstrap distribution were then used to determine the 95% Confidence Interval (CI) of the ROC.
All statistical analyses were performed using the SAS software package version 9.2 (SAS, Cary, North Carolina).

For the efficacy analysis, the primary analysis set was the full analysis set. Safety was analyzed based on the safety analysis set that consisted of patients who received at least one dose of the investigational drug. Descriptive statistics (e.g., mean, standard deviation, counts, and proportions) were summarized as appropriate. The primary endpoint was analyzed by one-sample Wilcoxon’s signed-rank test. The 9-year survival of patients was calculated according to the Kaplan–Meier method. The mitochondrial disorder severity scores and the migraine severity scores were analyzed by one-sample Wilcoxon’s signed-rank test. The improvement rates of headache and nausea/vomiting at 2 h after completion of the initial intravenous administration were calculated separately and analyzed by Fisher’s exact test. The multiplicity issue was adjusted according to the Hochberg procedure [17 (link)]. One-tailed t-test was conducted to examine the between-group difference with respect to the following two interictal phases: one between the day of first diagnosis and the day of first ictus; and another between 60 days prior to the day of first diagnosis and the day of first ictus. A value of p < 0.05 (one-tailed) was considered statistically significant. All statistical analyses were made with the SAS software package version 9.2 (SAS Institute, Cary, NC).

The results are expressed as the mean ± standard deviation (SD) of at least three independent experiments. Statistical differences between the groups were evaluated by one-way analysis of variance (ANOVA) followed by Duncan's multiple range test. Values of p < 0.05 were considered statistically significant. The statistical analysis system (SAS) software package version 9.2 (SAS Institute Inc., Cary, NC, USA) was used for the analysis.

Statistical analysis was performed using the SAS software package version 9.3 (SAS Inc, Cary, NC). Binary data are expressed as percentages (numerator/denominator numbers); for continuous variables such as age and hospital stay, median values with 25th and 75th percentiles (interquartile range) are shown. The descriptive statistics are based on the available cases, which are used as denominator of rates. The Pearson χ² test was used to examine differences between patient groups in categorical variables, and the Mann‐Whitney‐Wilcoxon test for metrically scaled variables. Statistical significance was defined as 2‐sided P≤0.05. Odds ratios (OR) with 95% CIs were calculated for the comparison of binary variables. OR with 95% CIs adjusted for age as a linear term were calculated by logistic regression for sex comparisons.

Rates of Apgar scores 0–3 at 5 and 10 minutes, meconium aspiration, and neonatal seizures were calculated as the proportion of infants with these outcomes in the study population. Logistic regression analyses were performed to estimate the risk of neonatal complications in different maternal BMI categories (underweight, overweight, and obesity grade Ι–ΙΙΙ) as compared with normal-weight women. The analyses were also performed with BMI as a continuous variable. In all analyses, the generalized estimating equation method was applied to correct for repeated pregnancies, using the GENMODE procedure. In the multivariable analyses, estimates were adjusted for maternal height, age, parity, smoking in early pregnancy, level of education, mother's country of birth, and year of infant birth. These variables were categorized and entered in the model as listed in Table 1. In a second multivariate model, odds ratios were also adjusted for mode of delivery. To explore potential contributions of maternal obesity-related diseases and congenital malformations, all analyses were repeated after excluding infants of women with chronic hypertension, preeclampsia, pregestational or gestational diabetes, and infants with malformations. All analyses were performed using SAS software package version 9.3 (SAS Institute, Inc.).

The SAS software package version 9.3 (SAS Institute, Cary, NC) was used to perform all statistical analyses. We assessed the statistical significance of differences in the prevalence or mean of each factor among the DR status groups by using a logistic or linear regression model, respectively. To analyze FPG, 2-hour PG, HbA_1c, GA, and 1,5-AG levels as categorical variables, these values were divided into ten groups on the basis of deciles. The receiver operating characteristic (ROC) curve analysis was performed to determine the optimal threshold of each glycemic measure for detecting the presence of DR. The optimal threshold was obtained from the point on the ROC curve closest to the ideal of 100% sensitivity and 100% specificity. The discrimination of each measure of glycemia for DR was assessed by the area under the ROC curve (AUC). The difference in the AUC was estimated using the method of DeLong et al. [38 (link)]. A value of p < 0.05 was considered statistically significant in all analyses.