Meta-Research: Why we need to report more than 'Data were Analyzed by t-tests or ANOVA'

Abstract

Transparent reporting is essential for the critical evaluation of studies. However, the reporting of statistical methods for studies in the biomedical sciences is often limited. This systematic review examines the quality of reporting for two statistical tests, t-tests and ANOVA, for papers published in a selection of physiology journals in June 2017. Of the 328 original research articles examined, 277 (84.5%) included an ANOVA or t-test or both. However, papers in our sample were routinely missing essential information about both types of tests: for example, 213 papers (95% of the papers that used ANOVA) did not contain the information needed to determine what type of ANOVA was performed, and 26.7% of papers did not specify what post-hoc test was performed. Most papers also omitted the information needed to verify ANOVA results. Essential information about t-tests was also missing in many papers. We conclude by discussing measures that could be taken to improve the quality of reporting.

Data availability

All data from the systematic review has been uploaded with the manuscript, along with the abstraction protocol.

Article and author information

Author details

  1. Tracey L Weissgerber

    Division of Nephrology and Hypertension, Mayo Clinic, Rochester, United States
    For correspondence
    weissgerber.tracey@mayo.edu
    Competing interests
    The authors declare that no competing interests exist.
    ORCID icon "This ORCID iD identifies the author of this article:" 0000-0002-7490-2600
  2. Oscar Alejandro Garcia Valencia

    Division of Nephrology and Hypertension, Mayo Clinic, Rochester, United States
    Competing interests
    The authors declare that no competing interests exist.
    ORCID icon "This ORCID iD identifies the author of this article:" 0000-0003-0186-9448
  3. Vesna D Garovic

    Division of Nephrology and Hypertension, Mayo Clinic, Rochester, United States
    Competing interests
    The authors declare that no competing interests exist.
  4. Natasa M Milic

    Division of Nephrology and Hypertension, Mayo Clinic, Rochester, United States
    Competing interests
    The authors declare that no competing interests exist.
  5. Stacey J Winham

    Division of Nephrology and Hypertension, Mayo Clinic, Rochester, United States
    Competing interests
    The authors declare that no competing interests exist.

Funding

American Heart Association (16GRNT30950002)

  • Tracey L Weissgerber

National Center for Advancing Translational Sciences (UL1 TR000135)

  • Tracey L Weissgerber

Mayo Clinic (Robert W. Fulk Career Development Award)

  • Tracey L Weissgerber

National Cancer Institute (R03-CA212127)

  • Stacey J Winham

Walter and Evelyn Simmers Career Development Award for Ovarian Cancer Research

  • Stacey J Winham

The funders had no role in study design, data collection and interpretation, or the decision to submit the work for publication.

Copyright

© 2018, Weissgerber et al.

This article is distributed under the terms of the Creative Commons Attribution License permitting unrestricted use and redistribution provided that the original author and source are credited.

Metrics

  • 54
    citations

Views, downloads and citations are aggregated across all versions of this paper published by eLife.

Download links

A two-part list of links to download the article, or parts of the article, in various formats.

Downloads (link to download the article as PDF)

Open citations (links to open the citations from this article in various online reference manager services)

Cite this article (links to download the citations from this article in formats compatible with various reference manager tools)

  1. Tracey L Weissgerber
  2. Oscar Alejandro Garcia Valencia
  3. Vesna D Garovic
  4. Natasa M Milic
  5. Stacey J Winham
(2018)
Meta-Research: Why we need to report more than 'Data were Analyzed by t-tests or ANOVA'
eLife 7:e36163.
https://doi.org/10.7554/eLife.36163
  1. Further reading

Further reading

    1. Medicine
    Feilin Cao, Zhaosheng Ma ... Shifen Huang
    Research Article

    Background:

    Approximately one-third of patients with HER2-positive breast cancer experienced recurrence within 10 years after receiving 1 year of adjuvant trastuzumab. The ExteNET study showed that 1 year of extended adjuvant neratinib after trastuzumab-based adjuvant therapy could reduce invasive disease-free survival (iDFS) events compared with placebo. This study investigated the efficacy and safety of pyrotinib, an irreversible pan-HER receptor tyrosine kinase inhibitor, after trastuzumab-based adjuvant therapy in patients with high-risk, HER2-positive early or locally advanced breast cancer.

    Methods:

    This multicenter phase II trial was conducted at 23 centers in China. After enrollment, patients received 1 year of extended adjuvant pyrotinib (400 mg/day), which should be initiated within 6 months after the completion of 1-year adjuvant therapy (trastuzumab alone or plus pertuzumab). The primary endpoint was 2-year iDFS rate.

    Results:

    Between January 2019 and February 2022, 141 eligible women were enrolled and treated. As of October 10, 2022, the median follow-up was 24 (interquartile range, 18.0–34.0) months. The 2-year iDFS rate was 94.59% (95% confidence interval [CI]: 88.97–97.38) in all patients, 94.90% (95% CI: 86.97–98.06) in patients who completed 1-year treatment, 90.32% (95% CI: 72.93–96.77) in patients who completed only 6-month treatment, 96.74% (95% CI: 87.57–99.18) in the hormone receptor (HR)-positive subgroup, 92.77% (95% CI: 83.48–96.93) in the HR-negative subgroup, 96.88% (95% CI: 79.82–99.55) in the lymph node-negative subgroup, 93.85% (95% CI: 86.81–97.20) in the lymph node-positive subgroup, 97.30% (95% CI: 82.32–99.61) in patients with adjuvant trastuzumab plus pertuzumab, and 93.48% (95% CI: 86.06–97.02) in patients with adjuvant trastuzumab. The most common adverse events were diarrhea (79.4%), fatigue (36.9%), lymphocyte count decreased (36.9%), nausea (33.3%), and hand-foot syndrome (33.3%).

    Conclusions:

    Extended adjuvant pyrotinib administrated after trastuzumab-based adjuvant therapy showed promising efficacy in patients with high-risk HER2-positive breast cancer. The follow-up is ongoing to determine the long-term benefit.

    Funding:

    No external funding was received for this work.

    Clinical trial number:

    ClinicalTrials.gov: NCT05880927

    1. Immunology and Inflammation
    2. Medicine
    Haiyi Fei, Xiaowen Lu ... Lingling Jiang
    Research Article

    Preeclampsia (PE), a major cause of maternal and perinatal mortality with highly heterogeneous causes and symptoms, is usually complicated by gestational diabetes mellitus (GDM). However, a comprehensive understanding of the immune microenvironment in the placenta of PE and the differences between PE and GDM is still lacking. In this study, cytometry by time of flight indicated that the frequencies of memory-like Th17 cells (CD45RACCR7+IL-17A+CD4+), memory-like CD8+ T cells (CD38+CXCR3CCR7+HeliosCD127CD8+) and pro-inflam Macs (CD206CD163CD38midCD107alowCD86midHLA-DRmidCD14+) were increased, while the frequencies of anti-inflam Macs (CD206+CD163CD86midCD33+HLA-DR+CD14+) and granulocyte myeloid-derived suppressor cells (gMDSCs, CD11b+CD15hiHLA-DRlow) were decreased in the placenta of PE compared with that of normal pregnancy (NP), but not in that of GDM or GDM&PE. The pro-inflam Macs were positively correlated with memory-like Th17 cells and memory-like CD8+ T cells but negatively correlated with gMDSCs. Single-cell RNA sequencing revealed that transferring the F4/80+CD206 pro-inflam Macs with a Folr2+Ccl7+Ccl8+C1qa+C1qb+C1qc+ phenotype from the uterus of PE mice to normal pregnant mice induced the production of memory-like IL-17a+Rora+Il1r1+TNF+Cxcr6+S100a4+CD44+ Th17 cells via IGF1–IGF1R, which contributed to the development and recurrence of PE. Pro-inflam Macs also induced the production of memory-like CD8+ T cells but inhibited the production of Ly6g+S100a8+S100a9+Retnlg+Wfdc21+ gMDSCs at the maternal–fetal interface, leading to PE-like symptoms in mice. In conclusion, this study revealed the PE-specific immune cell network, which was regulated by pro-inflam Macs, providing new ideas about the pathogenesis of PE.