It is remarkable that in the interpretation of scientific evidence, be it as reviewer
for a medical journal or as reader, clinicians appear to be the ones most impressed
by p-values and statistical significance, or the absence thereof. They attach in their
reviews and presentations more importance to it than epidemiologists and statisticians.
In fact, the latter groups often actively discourage the use, and certainly the overinterpretation
of significance testing, as reflected also in reporting guidelines such as STROBE,
which see the presentation of p-values in a scientific article as an option, not an
obligation. Since the first authoritative publications forcefully arguing against
the use of statistical significance testing appeared in the 1980s and 1990s, it is
worthwhile to wonder why p-values are still used, and why especially clinicians are
so enamoured with them. In this opinion piece I will explain why relying on statistical
testing is philosophically erroneous, how it will often lead to the wrong conclusions,
and I will give my layman's psychological explanation why this p-disease has a strong predilection for clinicians.
Keywords
To read this article in full you will need to make a payment
Purchase one-time access:
Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online accessOne-time access price info
- For academic or personal research use, select 'Academic and Personal'
- For corporate R&D use, select 'Corporate R&D Professionals'
Subscribe:
Subscribe to European Journal of Internal MedicineAlready a print subscriber? Claim online access
Already an online subscriber? Sign in
Register: Create an account
Institutional Access: Sign in to ScienceDirect
Suggested reading
- A biographical glimpse of William Sealy Gosset.Am Stat. 1984; 38: 179-183
- Significance questing.Ann Intern Med. 1986; 105: 445-447
- Confidence intervals for reporting results of clinical trials.Ann Intern Med. 1986; 105: 429-435
- Toward evidence-based medical statistics. 1: the P value fallacy.Ann Intern Med. 1999; 130: 995-1004
Article info
Publication history
Published online: August 26, 2016
Accepted:
August 8,
2016
Received:
July 28,
2016
Identification
Copyright
© 2016 European Federation of Internal Medicine. Published by Elsevier B.V. All rights reserved.
