Statistical Reporting Recommendations - AHA/ASA Journals

I see no requirement that there is any reporting on 100% recovery. How will we ever get there if leadership doesn't require reporting on 100% recovery? This is why survivors need to be in charge.

Statistical Reporting Recommendations - AHA/ASA Journals

Statistical analyses are a crucial component of the biomedical research process and are necessary to draw inferences from biomedical research data. The application of sound statistical methodology is a prerequisite for publication in the American Heart Association (AHA) journal portfolio.

Authors intending to submit manuscripts to any of the AHA journals for consideration are encouraged to review the Recommendations for Statistical Reporting in Cardiovascular Medicine developed by the AHA Scientific Publishing Committee Statistics Task Force. The Statistical Editors for Circulation Research have also prepared complementary specific recommendations for encouraging reproducibility, rigor, interpretability, and transparency through improved statistical reporting.

General statistical reporting recommendations are provided here for consideration when submitting manuscripts to AHA journals. Authors are encouraged to review each of the following sections as appropriate in the full Recommendations for Statistical Reporting in Cardiovascular Medicine for more detailed standards on high-quality reporting of statistical analyses methods and results.

1. General Standards
2. Observational Studies: Diagnostic Tests and Validation
3. Observational Studies: Clinical Prediction Models
4. Statistical Genetics
5. Randomized Controlled Trials
6. Systematic Reviews and Meta-Analyses
7. Survival Analyses
8. Bayesian Statistical Approaches
9. Missing Data
10. Correlated Data
11. Covariable Adjustment and Propensity Scores
12. Power and Sample Size Considerations

General Statistical Reporting Recommendations

1. Authors are encouraged to follow relevant existing reporting guidelines when applicable as listed on https://www.ahajournals.org/research-guidelines
2. Description of methods used to analyze data should be provided in sufficient detail that others can replicate the work.
3. Demographic information should be given for human specimens.
4. P-values must be reported to a minimum of two significant digits. When precise values don’t fit well in the figure, these can be included in a table or supplementary file; often scientific notation of small p-values improves presentation. It should be noted explicitly if p-values are raw or corrected.
• For example, in GraphPad, under “Options”, authors can select how many significant digits up to 15 digits. For very small p-values scientific notation improves readability. If the tool will provide authors with a test statistic, you may provide that or use an online tool or even Microsoft Excel to convert the statistic to a p-value.
• Given explicit information about the statistical approach and sample size, estimated effect sizes with confidence intervals can be reported as an alternative to p-values in some cases.
5. Exact sample size must be clearly described for every test and group.
6. Explicitly state power calculations, assumptions made by power calculations including effect size and significance threshold. If power calculations were not performed, state that. Power calculations can be performed using most statistical software, and many are available as webtools (for example http://powerandsamplesize.com/).
7. Data should be presented in a way that emphasizes completeness, informativeness, and truthfulness. In addition to general recommendations provided in the AHA Journal Figure Guidelines, please consider the following:
• To better display data density and distribution, dot plots, or violin plots for dense data, are preferred in lieu of bar charts.
• Error bars should be shown in both directions.
• For correlations, showing the scatter plot helps display the full relationship and may show outliers that are driving the correlation.
8. Authors will often present “representative” images to illustrate a key finding. The process used to select such “representative” images for display from the multiple choices should be described, and ideally, images from all replicates should be included in the supplementary materials.
9. Units should be clearly stated. Arbitrary and relative units must be clearly defined by stating the normalization procedures used. 
10. Common misapplied tests
• Parametric tests (e.g. t-test, ANOVA) when population mean normality has not been established and a non-parametric test should be used (e.g. Mann-Whitney, Wilcoxon rank sum)
• Using t-test to compare proportions when a chi-square or Fisher’s exact test of independence on exact count values should be used
• Two-way ANOVA vs. repeated measures ANOVA.
• Pearson correlations should be accompanied by a scatter plot and tests should be performed to identify the presence of outliers; if the correlation is being driven by outliers, use a non-parametric correlation test (e.g., Spearman’s rho or Kendall’s tau) instead.