Talk:David Firth (statistician)

I am the subject of this page. It needs to be deleted or improved.
Yesterday I emailed the Oversight group about this page. I am the subject of the page (let me know if anyone needs proof of that). Some edits were made yesterday by a member of the Oversight group, and I thank them for that. The purpose of my email yesterday was to request deletion of the page, and in the email I listed the problems with the page (as justification for my deletion request). The advice that I got back was that "Arguing you're not notable may be a hard sell", so deletion would probably not be allowed. The advice I got was to register an account and suggest improvements, instead.

My questions are:
 * was that good advice? (I have no reason to think otherwise, but I'd like to check)
 * if the page really cannot be deleted, then am I permitted (here, via the Talk) to suggest how to improve it? I am aware that it is not a good idea to actually edit a page about myself.

If I am permitted to make suggestions, then my proposal would be to use this page as a seemingly suitable template: https://en.wikipedia.org/wiki/Peter_McCullagh. I could aim to provide the factual information (and sources) needed to complete a page with headings like that one. Would that work?

I am completely new to Wikipedia, so please be gentle with me. Quasipolo (talk) 07:00, 15 November 2022 (UTC)


 * Welcome! Yes to both questions. The immediate direct answer is that you want the page WP:ERW.
 * It's not always a fast process, but it generally gets done faster the more specific you are about exactly what you want changed.
 * We also have a longer page about all the policies on this, in case you care to read that, but that's the super short version. &#x2130; mi1y&#x29fc;T&middot;C&#x29fd; 09:35, 15 November 2022 (UTC)
 * (p.s. to be clear, I'm not actually an admin, just saw a question I could answer.) &#x2130; mi1y&#x29fc;T&middot;C&#x29fd; 09:36, 15 November 2022 (UTC)
 * Thank you! That is very helpful, and much appreciated.  I will try to do as you suggested. Quasipolo (talk) 10:12, 15 November 2022 (UTC)
 * Thanks again for your help with this. I have submitted my edit request.
 * But now I am really worried, because the message I got back points to a list of around 260 requests ahead of mine --- requests which date back 6 months!
 * So now I feel like I should be insisting on deletion of the page, rather than waiting many months for my request to be reviewed. The very existence of the (as it stands) unimpressive Wikipedia page about me is damaging me, my job prospects, my chances of getting new funding for my work, etc.  I really feel like I am being bullied by Wikipedia, and I don't know what to do about it.  If anyone has any advice then I'd be really glad to hear it.
 * Quasipolo (talk) 22:35, 15 November 2022 (UTC)
 * As someone who works through edit requests sometimes, there's not really any rule imposing an order on them, and the non-COI ones tend to be easier to evaluate so we tend to focus on those.
 * I don't see anything immediately objectionable in your rewrite, and have applied it as is. &#x2130; mi1y&#x29fc;T&middot;C&#x29fd; 22:51, 15 November 2022 (UTC)
 * Oh wow -- thank you!! I really appreciate your help.  This is so much better than the dire warning about patience, and the 6-months backlog, had led me to expect.  I am very grateful. Quasipolo (talk) 23:03, 15 November 2022 (UTC)
 * from the edit history, I assume you were the oversighter who responded to this. Do you think the non-public information in the sentence starting with "He withdrew" (quoted again near the bottom of this page, I won't quote it again to make cleanup easier) is oversight-worthy? &#x2130; mi1y&#x29fc;T&middot;C&#x29fd; 23:38, 15 November 2022 (UTC)
 * The short answer to your question is no. Primefac (talk) 09:12, 16 November 2022 (UTC)

Conflict of Interest edit request
I am the subject of this page. I explain at the bottom here why the page needs to be improved. My suggestion is a complete re-write, and I have used this other page as a template: Peter_McCullagh.


 * What I think should be changed (include citations):

David Firth (born 22 December 1957) is a British statistician. He is Emeritus Professor in the Department of Statistics at the University of Warwick.

Firth was born and went to school in Wakefield. He studied Mathematics at the University of Cambridge and completed his PhD in Statistics at Imperial College London, supervised by Sir David Cox.

Firth is known for his development of a general method for reducing the bias of maximum likelihood estimation in parametric statistical models. The method has seen application in a wide variety of research fields, especially with logistic regression analysis where the reduced-bias estimates also have reduced variance and are always finite ; the latter property overcomes the frequently encountered problem of separation, which causes maximum likelihood estimates to be infinite. The original paper published in 1993 has been cited more than 4000 times according to Google Scholar.

Together with a PhD student, Renée de Menezes, Firth also established the generality of the method of quasi variances, a device for summarizing economically the estimated effects of a categorical predictor variable in a statistical model. .

Firth developed (in collaboration with John Curtice) a new statistical approach to the design and analysis of election-day exit polls for UK General Elections. The new methods have been used at UK General Elections since 2005 to produce the widely broadcast close-of-polls forecast of seats in the House of Commons. .

Firth was elected as a Fellow of the British Academy in 2008. He was the recipient of the Royal Statistical Society's Guy Medal in Bronze in 1998 and in Silver in 2012. With Dr Heather Turner he won the John M Chambers Statistical Software Award of the American Statistical Association in 2007, for the gnm package which facilitates working with generalized nonlinear models (a synthesis of nonlinear regression and generalized linear models) in R.

He is a former Editor of the Journal of the Royal Statistical Society, Series B (Statistical Methodology).


 * Google Scholar profile
 * Google Scholar profile


 * Why it should be changed:

Two days ago I emailed the Oversight group at Wikipedia, to request deletion of this page. The advice that I received in reply was that deletion would most likely not be possible because I am a notable academic person; instead, I was advised to set up a Wikipedia account and propose changes to the page (which is what I am doing now).

I will paste in, below, the part of my email from two days ago which lists the contents of the page and my comments on those contents. On Monday (14 Nov) someone in the Oversight group already made an edit that eliminated some of the problems. But other problems remain. The main problem is that the page, as it stands, makes my work appear not really notable, because its primary focus is on quasi-variances --- a relatively insignificant piece of work, compared to the bias-reduced maximum likelihood estimation method that is now very widely used (and which was not even mentioned). That is why (in my email message) I had suggested deletion of the page: it seemed the easiest solution to the problem. But if the page is not to be deleted, then I think it needs to be expanded as I am suggesting above.

I have tried (in the above) to suggest changes focused on the most important aspects of my work, and to provide published evidence for all of them. I have retained (in my suggested re-write) the part about quasi-variances, in order not to upset anyone (such as the originator of the page). I hope that I have succeeded in keeping everything neutral and factual.

Here, for full disclosure, is my critique of the page as it appeared on the morning of 14 November (ie, as in my email to the Oversight group):

-- The article is quite short so I will list here what's right or wrong about each part of it.


 * David Firth (born c. 1958) --- roughly correct (I was not born in 1958 but a nearby year) --- is a British statistician specialising in social-science and biostatistical applications. The second half of that is incorrect.  I actually work mostly on general statistical theory and methods.  I do not specialize in any application area.
 * He was president elect of the Royal Statistical Society. This is true.  But I never actually took up the presidency, so it hardly seems a notable fact?  (not as notable, I would have thought, as my election to Fellow of the British Academy several years ago)
 * was awarded their Guy Medal in Silver in 2012. This is true.  (also the Guy Medal in Bronze in an earlier year, but that omission is not why I want the page deleted)
 * He withdrew as president elect of the Royal Statistical Society for the 2023-2024 term for health reasons. This is true.  But the fact that I was unwell at any point in my life is surely private information, for me to disclose or not?  The reason for my withdrawal from the RSS presidency was made known to RSS members, only, because they needed to know it.  It should not be included here for all to see (my family, my friends, prospective employers, etc.).
 * Firth obtained his Ph.D. from the University of London in 1987 under the supervision of David Roxbee Cox. This is true.
 * Firth developed quasi-variance estimation. This is partly true (there is actually no estimation involved in the idea of quasi-variances).  But it is definitely not my most notable achievement, and in fact I'd argue that it's hardly notable at all as things stand.  In 50 years maybe the world will be using quasi-variances routinely and then my having invented it would become notable; but right now it's a relatively unknown method.  To highlight it here is to belittle my better-known work.
 * He also led the statistical team which worked with John Curtice to develop the successful exit polling methodology for UK general elections. This is partly true, but it reads as though I led a team of statisticians who developed that methodology.  The fact is that I developed it myself, without any other statistical input from others.  John Curtice was, and is, the leading expert on electoral politics; but the statistical development was all mine.

The article omits even a mention of my best-known research work (from the early 1990s), which is widely cited across many research disciplines. --

Quasipolo (talk) 21:25, 15 November 2022 (UTC)


 * Yes check.svg Done  &#x2130; mi1y&#x29fc;T&middot;C&#x29fd; 22:48, 15 November 2022 (UTC)