Sas software ver 9

Descriptive analysis was used to describe baseline characteristics and AEs. Survival curves were calculated using the Kaplan-Meier method. All statistical analyses were performed using SPSS statistical software ver. 25 (IBM Corp., Armonk, NY), SAS software ver. 9.4 (SAS Inc., Cary, NC), and R software ver. 3.5.0, (R Foundation for Statistical Computing, Vienna, Austria).
In prospective study, the following assumptions were made in the estimation of required sample size for primary end-point, PFS. The null hypothesis was that PFS (H₀) is 3.1 months. H₀ was estimated from the previous trial of interferon α with PFS of 3.1 months. If temsirolimus had PFS of less than 3.1 months, trial would not proceed. The alternative hypothesis (H₁) was that PFS will be 5.5 months for treatment-naïve patients. This was based on the previous study of treatment-naïve and previously treated RCC patients who had similar PFS of 5.5 months and 6.3 months, respectively [13 (link)]. Sample size was calculated using Simon’s optimal two-stage design. With one-sided significance level of 0.05, a power of 0.9 to reject the null hypothesis, and a 10% drop-out rate, the final sample size was calculated to be 30 patients.

Statistical analyses were performed using IBM SPSS Statistics ver. 25 (IBM Corp., Armonk, NY, USA) and SAS software ver. 9.4 (SAS Institute, Cary, NC, USA). Categorical variables were analyzed using the chi-square or Fisher exact test, and continuous variables were analyzed using the independent t-test or Mann-Whitney U-rank test. Survival curves and disease-free intervals were obtained using the Kaplan-Meier method. The differences in OS and DFS rates were assessed using the log-rank test. P-values less than 0.05 were considered to indicate statistical significance.
We estimated propensity scores with logistic regression to mitigate the confounding influence of the following covariates: tumor lesion, preoperative level of CEA, and operation technique, because these variables were significantly different between the monopolar energy group and advanced energy group in patient baseline characteristics. P-value for the Hosmer-Lemeshow goodness-of-fit test of propensity score matching model was 0.382. After matching, no significant differences in the baseline characteristics were shown.