WARNReviewer 1· 75% conf
Statistical tests are named for some analyses but inadequately, with no verification of assumptions, no exact p-values, and poor data presentation.
Evidence
direct quote[Results, Figures 6-8 legends]
“with significance set at **P < 0.05,***P < 0.01, ****P < 0.005”absence[Section 2.7]
Assumptions not addressed.paraphrase[Figures 5-8]
“Figures display bar graphs with error bars; no individual points shown.”WARNReviewer 2· 85% conf
Statistical tests are named, and software is identified, but assumptions are not verified, exact p-values are not reported (only thresholds), and effect sizes with confidence intervals are absent. Data presentation shows individual points in figures but error bars are not defined.
Evidence
direct quote[Methods, section 2.7]
“The χ2 test was used to assess the correlation between AKT3 expression and clinicopathological parameters. The Mann-Whitney U test or Kruskal-Wallis test was applied for other analyses.”direct quote[Results, sections 3.5-3.8]
“**P < 0.05,***P < 0.01, ****P < 0.005.”absence[Figure legends, Methods]
Error bars are not defined in figures or methods.FAILReviewer 3· 90% conf
Statistical reporting is severely deficient: tests are named but not linked to specific analyses, exact p-values are not reported, assumptions are not verified, effect sizes and confidence intervals are absent, and data presentation lacks individual data points.
Evidence
direct quote[Methods, section 2.7]
“The χ2 test was used to assess the correlation between AKT3 expression and clinicopathological parameters. The Mann-Whitney U test or Kruskal-Wallis test was applied for other analyses.”direct quote[Results, sections 3.5-3.8]
“***P < 0.01, ****P < 0.005”absence[Results, sections 3.5-3.8]
No effect sizes or confidence intervals are reported.