Reporting of statistical results in prosthodontic and implantology journals: p values or confidence intervals?

Interpretation of CIs in clinical trials with non-significant results: systematic review and recommendations

OBJECTIVES

Interpretation of CIs in randomised clinical trials (RCTs) with treatment effects that are not statistically significant can distinguish between results that are 'negative' (the data are not consistent with a clinically meaningful treatment effect) or 'inconclusive' (the data remain consistent with the possibility of a clinically meaningful treatment effect). This interpretation is important to ensure that potentially beneficial treatments are not prematurely abandoned in future research or clinical practice based on invalid conclusions.

DESIGN

Systematic review of RCT reports published in 2014 in Annals of Internal Medicine, New England Journal of Medicine, JAMA, JAMA Internal Medicine and The Lancet (n=247).

RESULTS

85 of 99 articles with statistically non-significant results reported CIs for the treatment effect. Only 17 of those 99 articles interpreted the CI. Of the 22 articles in which CIs indicated an inconclusive result, only four acknowledged that the study could not rule out a clinically meaningful treatment effect.

CONCLUSIONS

Interpretation of CIs is important but occurs infrequently in study reports of trials with treatment effects that are not statistically significant. Increased author interpretation of CIs could improve application of RCT results. Reporting recommendations are provided.

Misleading reporting and interpretation of results in major infertility journals

OBJECTIVE

To evaluate the proportion of randomized controlled trials (RCTs) published in top infertility journals indexed on PubMed that reported their results with proper effect estimates and their precision estimation, while correctly interpreting both measures.

DESIGN

Cross-sectional study evaluating all the RCTs published in top infertility journals during 2014.

SETTING

Not applicable.

PATIENT(S)

Not applicable.

INTERVENTION(S)

Not applicable.

MAIN OUTCOME MEASURE(S)

Proportion of RCTs that reported both relative and absolute effect size measures and its precision.

RESULT(S)

Among the 32 RCTs published in 2014 in the top infertility journals reviewed, 37.5% (95% confidence interval [CI], 21.1-56.3) did not mention in their abstracts whether the difference among the study arms was statistically or clinically significant, and only 6.3% (95% CI, 0.8-20.8) used a CI of the absolute difference. Similarly, in the results section, these elements were observed in 28.2% (95% CI, 13.7-46.7) and 15.6% (95% CI, 5.3-32.8), respectively. Only one study clearly expressed the minimal clinically important difference in their methods section, but we found related proxies in 53% (95% CI, 34.7-70.9). None of the studies used CIs to draw conclusions about the clinical or statistical significance. We found 13 studies where the interpretation of the findings could be misleading.

CONCLUSION(S)

Recommended reporting items are underused in top infertility journals, which could lead to misleading interpretations. Authors, reviewers, and editorial boards should emphasize their use to improve reporting quality.