Jmp ver 15

For continuous parameters, the Student’s t-test or Mann–Whitney U test was applied as appropriate after confirming normality for two-group comparisons, and the ANOVA or Kruskal–Wallis test was applied as appropriate after confirming normality for multi-group comparisons. For categorical parameters, the Pearson χ² test was applied to estimate group differences. For comparison of survival, the Kaplan–Meier method was applied and tested using the log-rank method. Data for continuous parameters were presented as median values (interquartile range, IQR). Multivariate logistic regression analysis linked to SARC-F ≥ 4 points or SARC-F ≥ 1 point was also performed to identify independent factors. The significance level was 0.05 by using JMP ver. 15 (SAS Institute Inc., Cary, NC, USA).

Shoot fresh weight data were analyzed using ANOVA in JMP (ver. 15) statistical package (SAS Institute Inc., Cary, NC, USA). Data was visualized using SigmaPlot (ver. 13) software (Systat Software Inc., San Jose, CA, USA). The assumptions of homoscedasticity and normality were met using Levene′s tests. For both experiments, i.e., the response of GO and GY populations to herbicide treatments at different growth stages and the synergistic effect of surfactant application, interactions between experimental parameters were observed. Thus, data from each experiment were analyzed separately as experiment-by-treatment. For all experiments, shoot fresh weight was analyzed as percent of untreated control. All parameters were subjected to one-way ANOVA and means were separated using the Tukey-HSD test (α = 0.05).

For analyzing continuous variables, the appropriate statistical method among Student's t test, Mann-Whitney U test and Spearman's rank correlation coefficient (r_s) was chosen in order to compare 2 groups. For analyzing categorical variables, Pearson χ² test was applied in order to evaluate between-group difference. For analyzing the significance of prognostic parameters, continuous parameters were divided into 2 groups at the median, and transformed into nominal variables. For the estimation of cumulative OS rate, we used the Kaplan-Meier method and tested by the log-rank test. A Cox proportional hazard model was applied for the multivariate analysis of parameters with a P value <0.05 in the univariate analysis. The observation period was defined as the time interval between the date of initial chemotherapy and the date of death or the last date of confirmed survival. In the data presentation, n (%) or median (interquartile range (IQR)) was used. Statistical software was JMP ver. 15 (SAS Institute Inc., Cary, NC), with a P value = 0.05 as the significance level.

Continuous variables showing a normal distribution were presented as the mean with the standard deviation. Other continuous variables were presented as medians with an interquartile range. Categorical variables such as the sex distribution, presence of infection, JCS, and cause of convulsion are presented as the number and percentage of the total study sample.
Results were evaluated by the positive likelihood ratio of PCT for the infection, which is defined as the proportion of “infection group” patients among the patients with a positive PCT value. The positive likelihood ratios of PCT for infections in the convulsion group and the non-convulsion group were compared. The cut-off of PCT was set as 0.5 ng/mL following the standard value of bacterial infection [13 (link),14 (link)]: PCT ≥ 0.5 ng/mL is positive; PCT < 0.5 ng/mL is negative. We also evaluated those data when setting the PCT cut-off line as PCT ≥ 1.0 ng/mL and ≥2.0 ng/mL as sensitivity analyses.
Significance was inferred for p < 0.05. Statistical analyses were conducted using software (JMP ver. 15; SAS Institute Inc., Tokyo, Japan).

In analyzing continuous variables, we selected the appropriate method among Student’s t test, Mann–Whitney U test or Pearson correlation coefficient r for comparing 2 groups, and also selected the appropriate method between ANOVA and Kruskal–Wallis test for comparing multiple groups. Variables with statistically significant correlation with the SARC-F score were entered into a multivariate regression analysis by the least square method, and candidate parameters were finally selected. A continuous variable was shown as a median with interquartile range (IQR). A p value of 0.05 was a threshold for significance by the JMP ver. 15 (SAS Institute Inc., Cary, NC, USA).