Article
Statistical misconceptions in medical research – ideas to effectively address them
Search Medline for
Authors
-
Sophie K. Piper
- Institute of Biometry and Clinical Epidemiology, Charite - Universitätsmedizin Berlin, Berlin, Deutschland
-
Oliver Schweizerhof
- Institute of Biometry and Clinical Epidemiology, Charite - Universitätsmedizin Berlin, Berlin, Deutschland
-
Bob Siegerink
- Charite - Universitätsmedizin Berlin, Center for Stroke Research Berlin (CSB), Clinical Epidemiology and Health Services Research in Stroke (CEHRIS), Berlin, Deutschland
-
Jessica Rohmann
- Charite - Universitätsmedizin Berlin, Center for Stroke Research Berlin (CSB), Berlin, Deutschland
-
Alice Schneider
- Institute of Biometry and Clinical Epidemiology, Charite - Universitätsmedizin Berlin, Berlin, Deutschland
-
Geraldine Rauch
- Institute of Biometry and Clinical Epidemiology, Charite - Universitätsmedizin Berlin, Berlin, Deutschland
-
Ulrike Grittner
- Institute of Biometry and Clinical Epidemiology, Charite - Universitätsmedizin Berlin, Berlin, Deutschland
| Published: | August 27, 2018 |
|---|
Outline
Text
Methodological competencies of both researcher and public are essential for the quality, credibility and correct interpretation of research results. Familiarity with key statistical and epidemiological concepts is integral to a project’s success. However, common misconceptions can lead to misuse of statistical and/or epidemiological methods in research, which consequently can lead to misinterpretation of the results. This, in turn, can lead to incorrect conclusions, have detrimental effects in the development of research fields, and may even negatively affect patient health. In recent years, many leading scientists have described a reproducibility crisis in multiple research fields [1], much of which may be preventable with the proper application of appropriate methodology [2]. The aim of our project is to address widespread misconceptions of medical students, doctors and biomedical researchers in a customized, inter-active manner.
We plan to create an adaptive web-based teaching tool consisting of specific multiple choice questions that address common malpractices and provide the corresponding background material individually in several steps ranging from hints over short explanations to longer tutorials, if needed, to improve statistical knowledge.
After identifying an individual’s knowledge gaps in statistical and epidemiological concepts relevant to medical and health sciences, this teaching tool will use a targeted, application-oriented approach to clarify specific concepts [3].
The authors declare that they have no competing interests
The authors declare that an ethics committee vote is not required.
This contribution has already been presented [4].
References
- 1.
- Ioannidis JPA. Why Most Published Research Findings Are False. PLOS Medicine. 2005;2(8):e124. DOI:10.1371/journal.pmed.0020124
- 2.
- Motulsky HJ. Common misconceptions about data analysis and statistics. Pharmacol Res Perspect. 2015;3(1):e00093. DOI:10.1002/prp2.93
- 3.
- Rauch G, Muche R, Vonthein R. Zeig mir Biostatistik! Berlin, Heidelberg: Springer; 2014.
- 4.
- Grittner U, Siegerink, B, Rohmann JL, Schneider A, Rauch G, Piper S. p-Hacking and other common forms of statistical malpracticein medical research – ideas to effectively address them. 64. Biometrisches Kolloquium 2018 in Frankfurt am Main
