Skip to main content
PMC home page
NIHPA Author Manuscripts logoLink to NIHPA Author Manuscripts
. Author manuscript; available in PMC: 2020 Jun 12.
Published in final edited form as: J Complement Integr Med. 2019 Jun 12;16(2):/j/jcim.2019.16.issue-2/jcim-2018-0037/jcim-2018-0037.xml. doi: 10.1515/jcim-2018-0037

Differences in Nominal Significance (DINS) Error leads to invalid conclusions: Letter regarding, “Diet enriched with fresh coconut decreases blood glucose levels and body weight in normal adults”

Cynthia M Kroeger 1,2,*, Andrew W Brown 3, David B Allison 2
PMCID: PMC6957306  NIHMSID: NIHMS1062227  PMID: 31199765

Vijayakumar et al. (1) conducted a parallel-arm, randomized, controlled trial to test the effects of fresh coconut versus groundnut and groundnut oil on differences in anthropometric and cardiometabolic outcomes. The parallel-arm, randomized, controlled design is well-suited to test for effects between groups, and the authors conducted between-group statistical tests (independent t tests). The data reported in Table 2 indicate that no statistically significant differences were observed among the coconut or groundnut groups for any outcome measures. However, the authors concluded that, “Daily consumption of 100 g of fresh coconut … is found to be beneficial in reducing body weight and blood glucose levels” and that “[r]esults of this study suggest that fresh coconut-added diet helps reduce blood glucose levels and body weight in normal healthy individuals.” These conclusions are based on within-group analyses, which has been well-described in the literature as invalid for between-group comparisons and tests of treatment effects in randomized, controlled trials (2, 3).

The error of drawing conclusions based on within-group analyses is known as the Differences in Nominal Significance (DINS) error (4). DINS errors are common within nutrition and obesity research (5) and have led to the correction (6) or retraction (7) of other papers in the field. DINS errors can distort the scientific record by inflating Type I error rates from the expected 5% (i.e., when alpha has been deemed 0.05) to rates as high as 50% when comparing two groups of equal sample sizes (3, 5, 8).

Because the data refute the conclusions drawn by Vijayakumar et al. as stated within the study abstract and full text, we believe the publication should be corrected or retracted. Such action is consistent with the Committee on Publication Ethics (COPE) guidelines (9). A valid conclusion would communicate the non-significant results of the between-groups tests, consistent with the randomized design.

Acknowledgements

Supported in part by the National Institutes of Health, grants F32DK107157, R25DK099080, and R25HL124208. The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health or any other organization.

Footnotes

Competing Interests

None pertinent.

References

  • 1.Vijayakumar V, Shankar NR, Mavathur R, Mooventhan A, Anju S, Manjunath NK. Diet enriched with fresh coconut decreases blood glucose levels and body weight in normal adults. J Complement Integr Med. 2018. [DOI] [PubMed] [Google Scholar]
  • 2.Gelman A, Stern H. The Difference Between “Significant” and “Not Significant” is not Itself Statistically Significant. The American Statistician. 2006;60(4):328–31. [Google Scholar]
  • 3.Bland JM, Altman DG. Comparisons against baseline within randomised groups are often used and can be highly misleading. Trials. 2011;12:264. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 4.Allison DB, Brown AW, George BJ, Kaiser KA. Reproducibility: A tragedy of errors. Nature. 2016;530(7588):27–9. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 5.George BJ, Beasley TM, Brown AW, Dawson J, Dimova R, Divers J, et al. Common scientific and statistical errors in obesity research. Obesity (Silver Spring). 2016;24(4):781–90. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 6.Allison DB, Antoine LH, George BJ. Incorrect statistical method in parallel-groups RCT led to unsubstantiated conclusions. Lipids Health Dis. 2016;15:77. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 7.Cassani RS, Fassini PG, Silvah JH, Lima CM, Marchini JS. Retraction Note: Impact of weight loss diet associated with flaxseed on inflammatory markers in men with cardiovascular risk factors: a clinical study. Nutr J. 2016;15(1):59. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 8.Bland JM, Altman DG. Best (but oft forgotten) practices: testing for treatment effects in randomized trials by separate analyses of changes from baseline in each group is a misleading approach. Am J Clin Nutr. 2015;102(5):991–4. [DOI] [PubMed] [Google Scholar]
  • 9.Committee on Publication Ethics (COPE). Retraction Guidelines [Available from: https://publicationethics.org/files/retraction%20guidelines.pdf.

RESOURCES