Feature Christmas 2025: Citation Millionaire

New Year’s resolutions to push you past Doug Altman’s 1 060 928 citations

Jonathan J Deeks, Gary S Collins

BMJ 2025; 391 doi: https://doi.org/10.1136/bmj.r2550 (Published 17 December 2025)Cite this as: BMJ 2025;391:r2550 

Is your aim to become a famous researcher with over 1 000 000 citations against your publications? Do you need help thinking of New Year’s resolutions to reach this target? Then this article is for you.

Alongside French philosopher Michel Foucault1 and Canadian computer scientist Yoshua Bengio,2 Doug Altman is one of three academics with over 1 000 000 citations recorded on Google Scholar,3 a milestone he achieved in April 2025. An internationally acclaimed statistician, Doug was The BMJ’s chief statistical adviser for over 20 years, and he conceived and led global initiatives to raise the standards for medical research.4

How was this landmark achieved? Drawing inspiration from Doug’s remarkable career, our collective 26 years of working with him, insights from the unfinished biography that he kindly left with one of us (GSC), and correspondence with his wife, Sue, we have characterised his philosophy as “ten tips for citation success” (box 1).

Box 1

Ten tips for citation success

• 1 Make time for writing
• 2 Enjoy reading and words
• 3 Write something you are passionate about
• 4 Write things people need to know about
• 5 Approach writing as an art
• 6 Choose your words wisely
• 7 Keep your words and sentences as simple as possible, as complex as necessary
• 8 Share drafts and get feedback from coauthors early
• 9 Be a collaborator that everybody wants to work with
• 10 Write papers that could become citation magnets

We recognise the irony of celebrating citations for a man who said, “All that citation index stuff is complete bollocks, of course.”5 Citations are incomplete, easily manipulated, and a function of career length. High citation counts are meaningful only in the context of doing good science, and setting a high citation target will not by itself make you a better scientist.

Yet, these numbers reflect an undeniable truth: Doug Altman shaped how medical research is conducted and reported. You may never reach 1 000 000 citations, but if you write with passion, collaborate generously, treat writing as an art, and produce work that is genuinely useful, you will maximise the impact of your work.

So, if your goal is genuine influence that results in citations, here is our take on the Altman blueprint.

1 Make time for writing

You need volume and consistency. Clearly, quantity does not equate to quality, and volume is not necessarily a target but a consequence of longevity as a researcher. The last time Doug updated his publication list (5 April 2017), he had 998 publications (fig 1); he was first author on 285.

But how did he do so much? His wife, Sue, says that he worked most of the time that he was awake, not something we would necessarily encourage. His first publication is not on Google Scholar—aged 15, he published a letter in the match programme of his beloved Arsenal FC, the editor clearly spotting a potential future statistician (fig 2, fig 3).

Writing thrives on routine. Block out dedicated time in your schedule. Protect it fiercely and avoid meetings in those periods. Some of this time will be spent staring at a blank screen, waiting for inspiration. That’s part of the process. Papers don’t write themselves; unless you consistently carve out time to work on them, they simply won’t get written.

2 Enjoy reading and words

Doug showed that becoming a skilled writer begins with being a fervent reader. His career began when mainframe computers required patience while waiting for code to run. He used this time to read, working with fellow statisticians to dissect flaws in published articles. Journal clubs are a great way to force yourself to read, learn to critically appraise research, and enjoy discussion. Communicating complex scientific ideas clearly is challenging, but reading a wide range of material exposes you to different writing styles, showing which approaches work and which do not.

3 Write something you are passionate about

Doug wrote because he cared. His frustration about the poor quality of statistics in journal articles fuelled his passion. He turned that anger into a lecture, and then into his first commissioned series of eight papers in The BMJ, under the title “Statistics and ethics in medical research.”678910111213

The unethical misuse of statistics underlined his deeply held belief in the importance of scientific integrity. He said, “To maximise the benefit to society, you need to not just do research but do it well,”4 and “What should we think about researchers who use the wrong techniques, use the right techniques wrongly, misinterpret their results, report their results selectively, cite the literature selectively, and draw unjustified conclusions? We should be appalled.”14

Being passionate often makes the writing process easier and more enjoyable, as ideas will typically flow more naturally. Readers can tell when the author has a genuine passion for the subject matter; it makes the paper and the message more compelling and persuasive.

4 Write things people need to know about

Doug knew that complaining about bad research wasn’t enough; he had to provide the solution, realising that researchers need instruction. By filling a void, he created work that was used, reused, and cited. His publications on reporting guidelines are his most influential work. He was instrumental behind initiatives like the CONSORT statement—“Readers should not have to infer what was probably done; they should be told explicitly.”15

Doug didn’t stop with leading the CONSORT statement.16 He proposed an extensive “explanation and elaboration” document to accompany it.1718 This approach is now standard, published alongside many reporting guideline papers, including PRISMA,19 STARD,20 STROBE,21 REMARK,22 SPIRIT,23 and TRIPOD.24

Not everyone will write a CONSORT16 or PRISMA25 statement. But, when writing your paper, consider what the reader needs to know and what key messages you want to convey, and then present them clearly. Use boxes, tables, and figures strategically to highlight and reinforce your message.

5 Approach writing as an art

Doug talked about writing as a form of sculpture, where authors and editors revisit the text repeatedly, starting with a large chisel, then using increasingly finer tools.26 He particularly liked crafting short sentences—and was amused by single word titles,27 a couple of which he managed to publish.28 He was alert to potentially ambiguous wording, often turning sentences around to improve their sense or make them shorter.

6 Choose your words wisely

Careful word choice is fundamental to effective scientific writing. The language you use not only conveys data and findings but also shapes how those ideas are interpreted, critiqued, and built on. Aim for precision in terminology to communicate concepts accurately and avoid ambiguity or misinterpretation. Keep your writing clear and concise so that complex arguments remain accessible to readers outside the immediate field. Be especially vigilant with statistical terms, which are often misused.29

Choose phrasing that reinforces credibility. Overly casual or imprecise language can weaken the perceived rigour of your work. Remember that scientific publications often serve as enduring references, so the words you choose may influence discourse for years. By writing simply and clearly, you can strengthen the impact of your work and contribute meaningfully to the advancement of knowledge.

7 Keep your words and sentences as simple as possible, as complex as necessary

The goal of scientific writing is to engage and be transparent, allowing readers to see the science clearly without stumbling over words, spin, or misdirection. Use simple language, removing barriers to understanding, and reserve complexity for defining precise concepts.

Doug’s style, especially in his method papers, was engaging. He often started with a question and wrote in the first and second person. He made the reader part of the conversation, which made his explanations easier to follow. Consider his very first 1977 methods paper, for example: “It is possible that I have given the impression that statistical principles are difficult to grasp or dangerous to use. This would be unfortunate. Used with care, statistical techniques provide a very powerful means of advancing the cause of rational and constructive medicine. Statistical methods provide rules for asking the right questions and producing reliable answers.”30

8 Share drafts early

Good papers are team efforts, and Doug exemplified this. He never lent his name to a manuscript. He read and edited every draft. His feedback could take time, but it was always insightful and improved the work. Make your coauthors do some work and give them deadlines. Coauthorship is not an automatic right; it is a status that must be earnt. As the International Committee of Medical Journal Editors guidelines note, authorship is based on “drafting the work or reviewing it critically for important intellectual content” (www.icmje.org).

Circulate drafts early to encourage feedback, allowing your coauthors to refine arguments, identify gaps, and strengthen the overall clarity of the work before ideas become fixed. Early sharing also fosters a sense of shared ownership and accountability, ensuring that all voices are integrated into the paper rather than added as afterthoughts. By incorporating diverse perspectives from the outset, the quality and rigour of the manuscript are enhanced, producing a stronger, more cohesive, and influential publication.

9 Be a collaborator that everybody wants to work with

Research thrives on trust, respect, and clear communication, so being a collaborator that everyone wants to work with is vital. Doug published with over 1600 coauthors from many countries.4 When people see you as constructive, reliable, and supportive, collaborations become more productive. The final work gains credibility and, hopefully, impact.

10 Write papers that become “citation magnets”

Citation magnets are papers that have longevity and utility. Clinical studies can age quickly; methods papers endure. Doug’s book Practical Statistics for Medical Research31 and the Bland-Altman method32 (the most cited paper in the Lancet) are timeless resources. Reporting guidelines rank among some of the most cited publications in the literature. Doug was instrumental in developing many of these, including CONSORT,16 PRISMA,30 SPIRIT,23 STARD,20 STROBE,21 and TRIPOD.33 Because journals mandate their use, authors cite them to indicate compliance. Doug has 13 citation magnets with over 10 000 citations (table 1).

Table 1 

Doug’s citation magnets (papers with >10 000 citations)

Publication	Citations (as of 16/12/25)
Moher D, et al. Preferred reporting items for systematic reviews and meta-analyses: the PRISMA statement. BMJ 2009;339:b253525	190 119*
Von Elm E, et al. The Strengthening the Reporting of Observational Studies in Epidemiology (STROBE) statement: guidelines for reporting observational studies. BMJ2007;339:b270034	69 460*
Higgins JPT, et al. Measuring inconsistency in meta-analyses. BMJ 2003;327:557-6035	61 835
Bland JM, Altman DG. Statistical methods for assessing agreement between two methods of clinical measurement. Lancet 1986;327:307-1032	58 967
Liberati A, et al. The PRISMA statement for reporting systematic reviews and meta-analyses of studies that evaluate healthcare interventions: explanation and elaboration. BMJ 2009;339:b270019	58 182*
Higgins JPT, et al. The Cochrane Collaboration’s tool for assessing risk of bias in randomised trials. BMJ 2011;343:d592836	35 772
Altman DG. Practical statistics for medical research. Chapman and Hall/CRC, 199131	27 390
Sterne JAC, et al. ROBINS-I: a tool for assessing risk of bias in non-randomised studies of interventions. BMJ 2016;355:i491937	18 021
Whiting PF, et al. QUADAS-2: a revised tool for the quality assessment of diagnostic accuracy studies. Annals of Internal Medicine 2011;155:529-3638	14 409
Vandenbroucke JP, et al. Strengthening the Reporting of Observational Studies in Epidemiology (STROBE): explanation and elaboration. International Journal of Surgery2014;12:1500-2421	13 310*
Bland JM, Altman DG. Measuring agreement in method comparison studies. Statistical Methods in Medical Research 1999;8:135-6039	11 125
Collins GS, et al. Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement. BMJ 2015;102:148-5840	10 933*
Moher D, et al. The CONSORT statement: revised recommendations for improving the quality of reports of parallel-group randomised trials. Lancet 2001; 357: 1191-119416	10 417*

Writing a citation magnet will typically depend on covering the right topic at the right moment, as well as including an element of luck. Nevertheless, by following these tips, you can lay a strong foundation that increases the likelihood of producing a paper that attracts substantial attention.