The web page for Nature volume 567 issue 7748 lists a comment called "Scientists rise up against statistical significance". If you click on the link you get an online article with that title, and at the end there is a note saying "Nature 567, 305-307 (2019) doi: 10.1038/d41586-019-00857-9". But the online article also has a link to a "PDF version" which appears to show the actual layout of pages 305 to 307 with the title "Retire statistical significance".

What is the correct citation for this paper? And why do publishers make our lives difficult?

  • 2
    I"d probably cite the print version of the title, with the rest of the print information (including page numbers), and then add "on-line version titled 'Scientists rise up against statistical significance' at" followed by the URL. Jul 8, 2019 at 1:36
  • @AndreasBlass, that is probably the answer. I'd also note that online things can change and print is less likely to.
    – Buffy
    Jul 8, 2019 at 10:59

1 Answer 1


You appear to have found something quite bizarre: not just this article, but many of the Nature "Comment" articles appear to be titled differently in their HTML and PDF versions!

So, how to sort such a bizarre occurrence out? In my opinion, it's ambiguous whether print or online is "definitive", since many journals do not even bother with a print edition any more, and following a DOI will take you to the HTML version.

Instead, I would revert to first principles on the purpose of citation: to enable a person to find the document that is being referenced. To this end, I suggest searching online (as somebody who might follow the citation would). Here, one finds that the HTML title predominates (perhaps unsurprisingly), and thus I would recommend using the online title in this case.

  • On the other hand, they can change the online title tomorrow, while the print version is more or less stable/reliable in the long run. Jul 25, 2019 at 4:09
  • 1
    @rg_software The actual print version, yes. The PDF is just as potentially unstable as the HTML. In both cases, you're counting on a commitment from the journal not to change things.
    – jakebeal
    Jul 25, 2019 at 10:39
  • @jakebeal A good answer. An alternative, suggested in a comment above by AndreasBlass , is to include both titles in the reference. Or the title could be omitted (which seems to be the referencing style used in Nature).
    – jon1000
    Sep 1, 2019 at 18:59

You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .