Statistical Data Editing in Scientific Articles

Abstract

Scientific journals are important scholarly forums for sharing research findings. Editors have important roles in safeguarding standards of scientific publication and should be familiar with correct presentation of results, among other core competencies. Editors do not have access to the raw data and should thus rely on clues in the submitted manuscripts. To identify probable errors, they should look for inconsistencies in presented results. Common statistical problems that can be picked up by a knowledgeable manuscript editor are discussed in this article. Manuscripts should contain a detailed section on statistical analyses of the data. Numbers should be reported with appropriate precisions. Standard error of the mean (SEM) should not be reported as an index of data dispersion. Mean (standard deviation [SD]) and median (interquartile range [IQR]) should be used for description of normally and non-normally distributed data, respectively. If possible, it is better to report 95% confidence interval (CI) for statistics, at least for main outcome variables. And, P values should be presented, and interpreted with caution, if there is a hypothesis. To advance knowledge and skills of their members, associations of journal editors are better to develop training courses on basic statistics and research methodology for non-experts. This would in turn improve research reporting and safeguard the body of scientific evidence.

Keywords: Confidence Intervals; Editorial Policies; Journalism; Normal Distribution; Peer Review; Statistics.

Fig. 1

Examples of correct use of error bars. Left panel: The original legend reads “Prevalence of respiratory symptoms among the garden and factory workers. Error bars represent 95% CI” (10). Note that the error bar for the prevalence of “chest tightness” in “garden workers” is truncated at zero, as a negative prevalence is meaningless. Right panel: The original legend reads “Comparison of the response amplitude (vertical axis) at different frequencies (2–8 kHz [This is the graph for 6 kHz.]) in the study groups receiving various doses of atorvastatin. Error bars represent 95% CI of the mean. N/S stands for normal saline” (11). Note that some of the error bars extend to areas with negative amplitude response, as unlike the prevalence, a negative amplitude response does make sense (re-used with permission in accordance with the terms of the Creative Commons Attribution-NonCommercial 4.0 International License). CI = confidence interval, N/S = normal saline, TTS = temporary threshold shift, PTS = permanent threshold shift.

Fig. 2

Part of a panel of Kaplan-Meier survival curves (17). Note the dotted curve crossing other 2 curves. This clearly violates the “proportional hazard” assumption made in Cox proportional hazards model (re-used with permission in accordance with the terms of the Creative Commons Attribution Non-Commercial License [http://creativecommons.org/licenses/by-nc/3.0/]). MELD = model for end-stage liver disease.