Saturday, 3 January 2015

Science by press release

Yesterday's Times has a front page story "Two thirds of cancer cases are the result of bad luck rather than poor lifestyle choices...". (paywall)

That doesn't match my preconceptions, so I looked for the story online.    The Independent and the Telegraph agree.  So does the Mail.  And the Express. And the Mirror.

Reuters' headline agrees, but its story suggests something a bit different - that two thirds of an abitrary selection of cancer types occur mainly at random.

The BBC speaks unambiguously of "most cancer types" and so does The Guardian.

The press release which must have given rise to this story features the phrase "two thirds of adult cancer incidence across tissues can be explained primarily by 'bad luck'".  I can't make much sense of "cancer incidence across tissues", so I can't blame the journalists for stumbling over it likewise.  But the reporters who got the story right must have managed to scan down to the paragraph where the press release explains that the researchers "found that 22 cancer types could be largely explained by the “bad luck” factor of random DNA mutations during cell division. The other nine cancer types had incidences higher than predicted by "bad luck" and were presumably due to a combination of bad luck plus environmental or inherited factors."

I emphasize that "two thirds of cancer types" is not at all the same as "two thirds of cancer cases".  Two rare cancers apparently unrelated to environmental factors will count for far fewer cases than one common cancer in the other category.

So what of the paper behind the press release?  Here's the abstract, with a paywalled link to the whole paper.  Or you can 'preview' the paper for free here, to the extent your conscience permits.  Supplementary data and methodology descriptions are here.

The hypothesis behind the paper is that cancer is to a large extent caused by errors arising during stem cell division, at a rate which is independent of the tissue type involved.  The researchers therefore obtain estimates of the lifetime number of stem cell divisions various tissue types, and plot that against lifetime cancer incidence, obtaining a significant-looking scatter plot (Figure 1 in the published paper).  So far so good.

But they've used a log-log plot, necessary to cover the orders of magnitude variations in the data.  Now, if you think, as the researchers apparently do, that cancer risk is proportional to number of stem cell divisions, it follows that the slope of a log-log plot should be unity.  It isn't, by eye it's more like two thirds.  The researchers, busy calculating a linear correlation between the log values seem not to have noticed this surprising result.  Instead they square the correlation to get an R2 of 65%, which may (it's not clear) be the source of the "two-thirds of cancer types" claim.

If so, that claim is based on a total failure of comprehension of what correlation means.  Imagine a hypothetical world in which cancer occurs during stem cell division with some significant probability only if a given environmental factor is present, and that environmental factor is present equally in all tissue types.  In this world cancer incidence across tissue types is perfectly correlated with the number of stem cell divisions, but nevertheless all cancer is caused by the environmental factor.

It's simply impossible to say anything about the importance of environmental factors in a statistical analysis without including those factors as an input to the analysis.

However, the press release also features the paragraph I quoted about 22 out of 31 cancer types being largely explained by bad luck.  Perhaps that's what they mean by two thirds.  To get this number, they devised an Extra Risk Score - ERS for short.  Then they used AI methods to divide cancer types into two types based on the ERS values.  So what's the ERS?  The Supplement describes it as "the (negative value of the) area of the rectangle formed in the upper-left quadrant of Fig. 1 by the two coordinates (in logarithmic scale) of a data point as its sides." That is, it's the product of the {base-10 logarithm of stem cell divisions} and the {base-10 logarithm of lifetime cancer risk}.   (The cancer risk logarithm is negative (or zero) since lifetime risk is less than (or equal to) one.)

Shorn of the detail, it's the product of two logarithms.  How does that make sense?  Multiplying two logarithms is bizarre; for all ordinary purposes you're supposed to add them.  For this analyis, a simple measure would seem to be the ratio of lifetime incidence to stem cell divisions, or you might prefer the log of that ratio, which would be the log of the incidence minus the log of the stem cell divisions.

(On further reflection, the number I'd use would be {log(1-incidence)/divisions}.  That doesn't give a defined answer for lifetime incidence of unity, but you can get a number by using an incidence of just less than unity.  Among the other cancer types, it picks out gallbladder cancer as having the highest environmental or heriditary risk, which is consistent with that cancer's unusual geographical variation of incidence.)

The Supplement attempts to justify multiplying the logarithms by explaining why dividing them woudn't make sense.  Which is a bit like advocating playing football in ballet shoes because it would be foolish to wear stilettos.

Whatever ERS calculation you used, the clustering method would still divide the cancers into two groups, because that's what clustering methods do, but different calculations would put different cancer types in the high-ERS group.  If you want, as the senior author does, to draw conclusions from composition of the high-ERS cluster, you need a sound justification for your ERS calculation.

__

To its credit, The Guardian has published a piece pointing out the correlation misunderstanding.  This piece is also highly unimpressed by the paper, and this review of it has mixed feelings.

Me, I suppose the underlying idea has some truth in it.  But the methodology is the worst I've ever seen in a prominently published paper.

Update: more commentary from Understanding Uncertainty and StatsGuy 

Update: Bradley J Fikes, author of this piece in the San Diego Union-Tribute, complains in comments here that the title of this post is ill-chosen.  He points out that he didn't write his story simply from the press release, but checked it with John Hopkins before it was published.  He's got a point about the title: more than half of what I say here is criticism of the paper not of the press release.



61 comments:

  1. > I can't make much sense of "cancer incidence across tissues"

    I read http://www.statsguy.co.uk/are-two-thirds-of-cancers-really-due-to-bad-luck/ which I found helpful. That, too, points out flaws in the press, though not quite the one you're talking about.

    That gets you some way back towards "of course lifestyle (etc) affects incidence". Although it looks like he blows it somewhat in the comments.

    ReplyDelete
  2. The bane of my life as a medical engineer was clinicians who were functionally innumerate and had little to no grasp of statistics.

    ReplyDelete
  3. http://www.statschat.org.nz/2015/01/03/cancer-isnt-just-bad-luck

    http://notstatschat.tumblr.com/post/106956046171/variation-explained-and-log-transformation

    ReplyDelete
  4. I want to take this time out as a cancer survivor to encourage women out there still suffering from this. The sad news about it is that i was diagnosed on my 36th birthday in 2008 and with stage 3 TNBC which after i made research was a very aggressive form of cancer at that point i decided and told myself i was going to die and that the end has finally come.All my life i never thought of having breast cancer because i was very active and i worked out at the gym several times every week and my diet was okay. In my search for a cure after 6 years of diagnosis and even after chemo spending thousands of dollars a church member told me about Dr kennedy who could help me with a permanent cure, i doubted this at first but i later gave it a try and today i proud to say i am a cancer survivor no nodes and i am totally free the new diagnosis confirmed it. Do not die in silence or ignorance reach him on (drkennedy118@gmail.com or whatsapp +16468833189) don't be shy just speak to someone today.

    ReplyDelete
  5. Get Live Cricket Score with Ball by ball Live Score & live cricket Streaming of all international and domestic cricket matches being played around the world. Cricket Scorecard will be updated instantly and accuracy is given high importance.

    ReplyDelete
  6. Thanks for your marvelous posting! I seriously enjoyed reading it, you will be a great author.
    I will make sure to bookmark your blog and may come
    back later in life. I want to encourage continue your great posts,
    have a nice evening!

    India vs Pakistan Live
    Gold Cup 2017 Live

    ReplyDelete
  7. Boxing news, live streaming, videos, highlights results and reaction at BT Sport, the home of big-time ... Floyd Mayweather v Conor McGregor: Behind the scenes.
    floydmayweathervsconormcgregor2017.com

    buy boxing tickets

    ReplyDelete
  8. hRight Place To Watch Mayweather vs McGregor Live Stream.Mayweather vs McGregor Live Stream will held on August 26, 2017 http://www.mayweathervsmcgregorlivefreestream.com

    ReplyDelete
  9. You make me speechless with your ideas and amazing blog. Looking forward for your next blog. I become a great fan of you.



    Bluehost Discount Coupons

    ReplyDelete
  10. NDA Admit Card 2017 has been uploaded via online mode on the official portal of UPSC, Get updates for NDA Hall Ticket 2018, NDA Exam Admit card dates & how to download UPSC NDA admit 2017.

    ReplyDelete
  11. Hi, thanks for this awesome article, I’m Shania Kubisch 41 and from Manteca CA, USA. i was first diagnosed of Meniere’s disease in 2009 following an unexpected attack. My husband didn’t know what it was and i was taken to the hospital where we were told that i had meniere's disease. It lasted 2 years and went away. It came back in 2012 with a vengeance spinning 24/7, constantly feeling sick, tinnitus in my right ear, and loss of hearing. I was so devastated as i watched my carrier as a cashier crumble and communication with my family and friends lowered. After years of going to the ENT, and search for cure that proved abortive, my husband found out in a post on a health forum about some guru man (Prof Aafiya) who casts herbal healing spells to heal all kind of diseases. My family needed me and i needed a cure at all cost, i and my husband agreed to try the healing spell too and he complained my health state to the spell guru (prof Aafiya) on +2348108647815. He surely did help me and my husband cast a healing spell for Meniere's and i was completely healed of the disease just within 14 days. It’s been 2 years and 7 months since i had the healing spell and i have not had any symptoms of meniere’s disease. My hearing has been fully restored instantly and everything is back to normal again. If you have meniere's disease and experiencing it symptoms, you too may be able to get help from this Man (Prof Aafiya) via his email, prof.aafiyahealingspells@gmail.com .
    I now believe in super-naturalistic healing very much because my own case has proved to me that there is nothing impossible. Once again thanks for this great article.

    ReplyDelete
  12. This is so pretty, ! You’re so talented. I love all the little figures and colors. Adorable Hugs.

    Get Natural And home Remedies

    ReplyDelete
  13. Great idea. Thank you so much for sharing. Now I can save more things. Thanks again.

    http://www.beingglamour.com/

    ReplyDelete
  14. You make me speechless with your ideas and amazing blog. Looking forward for your next blog. I become a great fan of you.

    Wifi ranger extender

    ReplyDelete
  15. Your talent makes me sin! Covet, covet, covet!!!! But I will try to be happy for you. Thank you for sharing and inspiring!

    Power Enrich

    ReplyDelete
  16. Thanks for this wonderful post! I seriously enjoyed reading it, you will be a great author.

    Rapid Tone Weight Loss Diet

    Keto Tone Free Trial

    ProDiet Plus Weight Loss



    ReplyDelete
  17. Get all the solution of your question on this site and get details how to install router.

    My wifi installation

    ReplyDelete
  18. Get latest update on all sports like WWE Wrestling, Wrestlemania, Motogp, Formula 1 live streaming, Cricket, Football, Tennis, Hockey and more at
    Free motogp live stream

    Formula 1 Race results

    monday night raw results

    ReplyDelete
  19. The Sag Awards 2019 entries have been shut down at 22nd October 2018.
    Watch Sag Awards 2019

    ReplyDelete
  20. Thanks for this great post, i find it very interesting.
    www.mywifiext.net

    ReplyDelete
  21. Best Home Packers and Movers are the leading Packers and Movers Senapati Bapat Road, They give fantastic shifting administrations. We are the customary, steady packers movers office in Pune, notwithstanding we'll escape the shifting produced merchandise and gear with most noteworthy consideration and transport on schedule.
    Packers and Movers Senapati Bapat Road

    ReplyDelete
  22. I love the vital material offer in your article.
    I'll take a note of your web site as well as inspect once again below daily.
    www.fortivacreditcard.com

    ReplyDelete
  23. Fantastic blog you have here. Great article. please keep it up such great work.
    Kindly have a look on below link i hope it will be very useful for you.
    HOW TO FORCE THE NINTENDO SWITCH TO RESTART

    ReplyDelete
  24. mywifiext.net helps us to keep the network, PC and mobile phones connected with a guarded connection. new extender setup will help you in giving wifi at extended scope on every corner of your home.
    netgear WiFi extender setup

    You can also take guidance from our site netgear ex3700 setup. If still, you are facing issues while installing extender, then you have to contact our technical team on toll-free number 1-866-606-3055. Because it can be due to a router extender connection problem or any malicious software on connecting computer causing a concern. In case, have any issue you can contact our technical team.

    www.mywifiext.net ex3700

    netgear ac750 ex3700

    netgear n300 setup

    netgear n300 wifi range extender setup

    netgear n300 wifi extender setup

    netgear n300 extender setup

    netgear extender setup

    new extender setup

    netgear wifi extender setup

    netgear_ext

    netgear extender login

    netgear wifi extender login

    netgear extender

    Mywifiext.net

    mywifiext

    mywifiext net

    www.mywifiext.net

    ReplyDelete
  25. Best mac cleaner
    Best Home Packers and Movers are the leading Packers and Movers Senapati Bapat Road, They give fantastic shifting administrations. We are the customary, steady packers movers office in Pune, notwithstanding we'll escape the shifting produced merchandise and gear with most noteworthy consideration and transport on schedule.

    ReplyDelete


  26. Thanks for sharing useful information...We all usually choose the WPS option to setup wi-fi range extenders. Well, no problem as such but at times your Netgear extender stops working all of a sudden. To rescue from this trouble, you can try to set up Netgear extender not working manually.
    https://routererrorcode.com/blog/netgear-extender-not-working/

    ReplyDelete
  27. Our Escorts in Gurgaon services conferred are not to be too expensive it will be always afforded to your pocket. Choosing any of the time of the day you will specifically create a selection from our Gurgaon photos gallery. Just in any case you need a spectacular escort’s service in Gurgaon for any special day, you will hire a special girl anytime. Please go to the escort gallery of our website for sexiest call girls in Gurgaon. Every professional man has different choices someone like fat women whereas some like slender girls with big curves. Some are prone to mature ladies whereas some like company of young women. No matter be your personal want, you’ll be at liberty to contact Gurgaon Escorts and call girls at no matter time you would like we are open 24X7 to assist you and to fulfill your desires, your feelings, and your willingness. You’ll delicately discuss details with the employees that are each useful and passionate.

    Model escorts in gurgaon

    Callgirls in gurgaon

    Housewifes in gurgaon

    Gurgaon escorts

    College girls in gurgaon

    ReplyDelete
  28. I really like this concept. Hoping to continue the new ideas with professional excellence. Thanks for sharing.

    getmyoffer capitalone com
    azpeople
    getipass login

    ReplyDelete
  29. On our site you will find a huge collection of Shayari Kitab

    ReplyDelete
  30. Garmin.com/express Garmin.com/Express Download Garmin Express To Install & Manage Garmin Updates For all Garmin Devices With Easy Instruction by visiting garmin.com/express.

    ReplyDelete
  31. Magellan Gps Update Magellan Gps Update is a prominent portable GPS navigation consumer electronics company. To take the benefits of the Magellan GPS device, the users have to install and get the latest Magellan GPS updates. Through the GPS Magellan updates, the user can have an up-to-date version of the GPS device. In the year 1986, the company was established, and the Head Quarter is in San Dimas, California.

    ReplyDelete
  32. Garmin Express Garmin express - Register, update and sync your device with Garmin. Manage devices from your desktop. Garmin Express is a computer application.

    ReplyDelete
  33. office.com/setup office.com/setup - For Office Setup and Activation go to www.office.com/setup and get started with activation and installation by entering product key.

    ReplyDelete
  34. Rand Mcnally Dock Update Rand McNally is a world-leader in providing GPS based Navigation Devices. Its innovative product range covers the diverse needs of various users. These intuitive, user-friendly devices are designed to eliminate stressful navigation out of your travels. However,

    ReplyDelete
  35. UFC 251 Live Time
    After postponing comings and goings earlier this year due to the coronavirus outbreak, UFC CEO Dana White wasted no period in getting things urge going regarding for taking place and approach. White promised MMA fans that the UFC would be the first sports league to start hosting stir behavior again, and even hinted a private Fight Island would dispel as a venue for well ahead shows. That become earliest has finally arrive: On Saturday, July 11, UFC 251 is hosting three explosive championship matches at Yas Island in the United Arab Emirates. Most UFC pay-per-views feature at least one championship bout, and sometimes, MMA fans will profit privileged taking into account two title fights. The star-studded UFC 251 fight card boasts not two but three contests for the mens welterweight, featherweight, and bantamweight belts, as skillfully as a intensely anticipated rematch together along together in the company of former womens strawweight champions Jssica Andrade and Rose Namajunas.

    ReplyDelete
  36. Canon Pix-ma printers are a part of a category of the simplest all-in-one printers within the market. Founded on a new creativity, Canon printers are divided into office and photo printing. a glance at each design will tell you ways sleek Canon printers can become as they need the simplest printer designs found during a multi-function and special photo printers. Canon.com/ijsetup | Ij.start.cannon | AOL Mail | aol mail | Garmin.com/Express | Rand McNally GPS Update | Norton.com/nu16

    ReplyDelete