Jump to content

Property:Specifications on analyses

From CAMIH

This is a property of type Text.

Showing 20 pages using this property.
S
Measures of central tendency were computed and frequencies and distributions produced for demographic and clinical characteristics of the study participants and checked for missing values, normalcy and outliers, where appropriate, using the Shapiro–Wilk statistic for the normality test and pearson’s chi-square test for skewness and kurtosis.  +
n for ITT: 243, only for tests between THC/Cannabis extract vs. Placebo n for PP: 80, tests between THC vs. Cannabis extract ITT and PP only for primary endpoint, sucessive testing labeled explorative  +
Independent sample t-tests or Wilcoxon tests were used to compare continuous variables between groups, and paired t-test or Wilcoxon tests were used for comparison within groups. For the categorical variable analysis, a χ<sup>2</sup> test or exact test were used for comparisons between groups. The Cochran-Mantel-Haenszel-χ2 test was used to analyze ordinal categorical data. Data were presented as the mean±standard deviation. P<0.05 was considered to indicate a significantly significant result.  +
T
ITT analysis for all 3 outcomes strictly overlapped with secondary analysis (PP), therefore only ITT analysis presented by authors  +
U
All patients who underwent randomization were included in the analysis; Relapse- and death-related outcomes were assessed according to randomization arm whether or not supplements were taken, whereas adverse events were assessed only in patients who continued to take the supplements (per protocol)  +
All statistical analyses were performed using STATA version 15.1. P values less than 0.05 were considered significant. Demographic data of all participants were analyzed by using mean, 95%CI, and percentage. Nausea score from day 1 to day 5 was showed in mean, and analysis of variance (ANOVA) for a 2 × 2 crossover study was analyzed comparing treatment, sequence, and period effect. Nausea grading for each day was compared using proportion f grading between treatment after adjusted sequence and period by using random-effects ordered logistic regression. Vomiting and side effects were analyzed by comparing percentages between groups using random-effects logistic regression.  +
V
Event-free survival, time to second primary tumor, and survival curves were constructed by the Kaplan–Meier technique and were compared by the log-rank test. The interaction between the effects of N-acetylcysteine and those of retinyl palmitate was tested with a proportional hazards model. Also, analyses of four arms were performed.  +
The specific analysis method is not stated in the study, however, according to the authors, all included patients were evaluated at the end of the study; comparison of the arms with chi-square test and exact fisher test  +