No. This is not acceptable.
The methods section is the single most important part of a scientific paper.
If those details are relegated to supplementary materials, then it's not a scientific paper in a scientific journal.
Kevin McConway
Kevin McConway (born 12 October 1950) is emeritus professor of applied statistics at the Open University, where he spent most of his career. He was the first Vice President (Academic Affairs) of the Royal Statistical Society, from 2012-2016. More on Wikipedia
-
Kevin McConway reposted
Peter Tennant has moved to Bluesky
@PWGTennant
This media couldn't be displayed. See it on the original post. -
Kevin McConway reposted
David Spiegelhalter
@d_spiegel
I am so pleased to see this! You and the whole team deserve the gratitude of the whole country
-
Kevin McConway reposted
Yoseph Araya
@YNAraya
Ageing well by connecting and learning about nature outdoors -
www.open.edu/openlearn/science-maths-technology/ageing-we… with @JitkaVseteckova and Ellie from @TheParksTrust -
Kevin McConway reposted
ASA History of Statistics Special Interest Group
@HOS_ASA
#otd 1948 Douglas G Altman b (d 3 June 2018)🇬🇧Co-founder of the Equator Network. “One of the most influential medical statisticians of the past 50 years” he spearheaded massive reforms in medical research reliability & role of reporting guidelines. 1/6🧵
-
Kevin McConway reposted
ABSW
@absw
Don't miss our next members' event with @kjm2 book now www.absw.org.uk/events/statistics-update-and-clinic
-
Kevin McConway reposted
RSS Data Ethics and Governance Section
@RSS_DatEthGov
The @NewtonGateway is running a 3-day virtual study group next week with 3 challenges from @anducnguyen @HardingProf and @StatsRegulation realating to how complex mathematical work is communicated and propagated. Still time to register and get involved:
gateway.newton.ac.uk/event/tgm122 -
Kevin McConway
@kjm2
Similar pattern on incidence (new infections) in this week's @ONS infection survey results as last week. Total modelled new infections for latest week available (ending 9 March) from ONS is about 3.1m, with wide error margin. New cases on dashboard for that week about 380k.
1/nPost not available here, view on X
Kevin McConway
@kjm2
..then the previous week, and despite the error margins, that must surely be a real and large increase (in early
March).
4/n
Kevin McConway
@kjm2
Graph of the ratio (just for England) of 'official' incidence estimates (new infections) from ONS to dashboard new cases
5/5 -
Kevin McConway
@kjm2
Today's @ONS Covid-19 survey results show something interesting in the incidence (new cases) estimates. They are always behind the positivity estimates for technical reasons - this week they go up to 26 Feb with modelled estimates up to 2 March. Historically they've usually..
1/nPost not available here, view on X
Kevin McConway
@kjm2
...margin of error) and the dashboard has about 250k, so survey has 8 times as many. Not just rogue week - the proportion has been changing in that dirn for over a month. Presumably because people aren't being routinely tested &/or not reporting LFDs. On the bright(?) side..
3/n
Kevin McConway
@kjm2
...it could mean that some of the recent increase in dashboard cases is because of more testing than real new cases (though I'm sure that most of it is likely to be real).
4/4 -
Kevin McConway reposted
Alessandro Vespignani
@alexvespi
“Investing in random sampling can better prepare governments for the future” by @nataliexdean
www.nature.com/articles/d41586-022-00336-8 -
Kevin McConway
@kjm2
Has something happened to the @Eurostar Android app? I tried to save some tickets from it to Gpay, nothing happened. So I tried to check on the Play Store whether there was an upgrade, Search for Eurostar revealed nothing, and links to app on Eurostar website said URL not found.
-
Kevin McConway reposted
Tom Forth
@thomasforth
My strongest possible agree with this piece. And then even more times ten. The ONS has improved from good to excellent in the past 5-10 years. On regional statistics. The website. The accessibility. And it overachieved enormously during Covid. www.economist.com/britain/2022/01/22/britains-office-for-…
-
Kevin McConway reposted
involve
@involveUK
. @CamdenCouncil has agreed a new Data Charter, drafted by a Residents’ Panel www.involve.org.uk/resources/blog/news/developing-data-ch… The development of the Charter didn’t happen in darkened rooms, hidden in the Council buildings. #open #transparent #democracy
-
Kevin McConway
@kjm2
ONS's new estimates from their Coronavirus Infection Survey cover the week to 23 December. Not so much detail even as last week's interim results. But estimated numbers who would test +ve is up by more than half a million on the estimate for 13-19 December.
Office for National Statistics (ONS)
@ONS
Latest #covid19 estimates show infection rates increased across all four countries of the UK in the week ending 23 Dec 2021 www.ons.gov.uk/peoplepopulationandcommunity/healthandsoci…
Post not available here, view on X
Kevin McConway
@kjm2
I've been asked whether the rest of the UK, or of England, will follow the pattern in London. I can't be sure, but don't forget London is a lot different from the other English regions in many ways. Different mixing patterns, demographic differences e.g. younger population. ...
Kevin McConway
@kjm2
...In UK as a whole, about 1 person in 7 is aged 70+, and that's also true for most English regions and for Scotland. Slightly more 70+ in Wales and SW England (1 in 6) and slightly fewer in NI (1 in 8). But in London it's 1 in 12. (Based on @ONS mid-2020 popn estimates.)...
Kevin McConway
@kjm2
...But vax rates a lot different too. In all English regions but two, according to the Govt dashboard for 29/12, between 50% and 60% of 12+ have had 3rd jab. Same for Wales and NI. SW England is 61%, Scot is 62%.
London is 38%. -
Kevin McConway reposted
John Roberts
@john_actuary
Some very dodgy maths in the @Mailonline suggesting that two thirds of those admitted with COVID recently were actually admitted for another reason.
It's nonsense, as all they have done is difference the figures between the two dates.
Let's take a look.
1/ -
Kevin McConway
@kjm2
Having published most of their usual weekly detail on the Coronavirus Infection survey a day early yesterday, @ONS have put out a briefer interim analysis today, x.com/ONS/status/1474349435706613825.
Office for National Statistics (ONS)
@ONS
Today we’ve published interim estimates of #covid19 positivity between 13 and 19 December 2021.
The number of people testing positive for COVID-19 increased in all four UK nations, as did the number of infections compatible with the Omicron variant www.ons.gov.uk/peoplepopulationandcommunity/healthandsoci…Post not available here, view on X
Kevin McConway
@kjm2
Also Omicron dominates (in sense of having higher estd. infections that from Delta) in England and in Scotland, and in 5 of the 9 English regions (using 19 Dec estimates), and is coming up fast elsewhere. In London, estd % testing +ve for Omicron doubled between 16 and 19 Dec...
Kevin McConway
@kjm2
...according to these @ONS estimates, though there's statistical uncertainty. But what's concerning is that the Delta estimates for London are rising too (since 11 Dec). Statistical uncertainty means that ONS might say the Delta trend is 'uncertain', but no evidence it's falling.
-
Kevin McConway
@kjm2
The @ONS weekly infection survey results out a day early this week because of Christmas. Their thread starts at x.com/ONS/status/1473987062688796673, NB not their currently pinned tweet which is about last week's results.
Office for National Statistics (ONS)
@ONS
Latest #covid19 estimates show in the week ending 16 December 2021, infections increased in England and Scotland ⬆️
In Wales and Northern Ireland, the trend was uncertain www.ons.gov.uk/peoplepopulationandcommunity/healthandsoci…Post not available here, view on X
Kevin McConway
@kjm2
Headlines include that the proportion of the population who would test +ve is up in England and Scotland in the latest week (10-16 Dec), trend uncertain in Wales and NI. In England the estimated proportion is 1 in 45, highest is has ever been since survey started in April 2020.
Kevin McConway
@kjm2
Also much evidence of the rise of Omicron. In London, by 16 Dec, ONS estimate that almost 1 in 20 of population aged 2+ would test +ve for Omicron, plus about 1 in 70 testing +ve for Delta. (Based on S gene target failure so the variant ID may not be perfect, but near enough.)
Post not available here, view on X
Kevin McConway
@kjm2
... the chance of testing positive with an Omicron-compatible result was lower in school age (& younger) children than in other ages, but that's based on data only up to 12 Dec and on a smallish number of observed Omicron cases, so things might change (or not) in that respect.
Kevin McConway
@kjm2
I'd previously have made points like this in comments for @SMC_London, which might or might not have been picked up in the media. But SMC are on their Xmas break (but still dealing with important breaking news) and I wanted to give them a rest! Also some journos are on hols too.
-
Kevin McConway
@kjm2
Odd thing about this booster push. You can't be boosted until 2 months after 2nd dose, so people who had not had that by 31 Oct (approx) can be boosted before year end. In England, by then 38m people had had 2 doses. By 12 December, 19.7m had already had 3 doses, so that...
1/nPost not available here, view on X
Kevin McConway
@kjm2
...in England. We don't know how many there are: ONS estimated 44.4m at mid-2020, and NIMS estimates 50m. Truth is probably somewhere between. But even if it's only 44.4m, that leaves 6.4m who can't be boosted by 31 Dec because they won't be eligible by then. Can't even...
3/n
Kevin McConway
@kjm2
...offer appointments for many of them because you can't even work out when they will be eligible until they have had 2nd dose. Seems like a big gap in the aim.
Doubtless I'm not the first to have thought this - apologies to whoever was first.
4/4 -
Kevin McConway reposted
RSS Data Ethics and Governance Section
@RSS_DatEthGov
Following the Bond review of mathematical science, and the big mathematics initiative, the CMS is consulting on a green paper proposal for a new National Academy. We note ethics is not mentioned in the proposal, but RSS member views are being sought now:
rss.org.uk/news-publication/news-publications/2021/genera… -
Kevin McConway
@kjm2
Article by @ChrisGiles_ and @SarahNev in the FT, Tues, www.ft.com/content/05e32f95-0e7e-4d2a-b408-6ec6035dea8e, and many tweets by Chris. Also article today by @katlay,Times, making similar points. Both say that deaths in England and Wales, &/or UK, are running above 5-year average so there are excess deaths.
Post not available here, view on X
Kevin McConway
@kjm2
So not much help for very short-term trends. But you can get data by date of occurrence from the @ONS bulletins, split into those that mention Covid on the certificate, and those that don't, and you can also get 5-year averages by date of occurrence from www.ons.gov.uk/peoplepopulationandcommunity/birthsdeathsa…
Kevin McConway
@kjm2
That is the results of an ad hoc data request, not from me. Hat tip to David Leon of LSHTM who told me about it last year. I've just checked again with @ONS that it's really classified by date of occurrence, not of registration, and they assure me it is. So I can do the excess...
Post not available here, view on X
Kevin McConway
@kjm2
The July week was very hot and that could be why deaths were very high. I don't know about the other one. And in general I don't know the reason for the difference in interpretation. It isn't the same as the actuaries' reason (because they used registrations and conclude that the
Kevin McConway
@kjm2
I checked, the September week was very hot too, temperatures up to 30 or so. Deaths have always spiked in heat waves.
Post not available here, view on X
Kevin McConway
@kjm2
My suspicion (no more than a vague one) is that it has something to do with differences in registration delays between deaths with different causes, particularly if that applies to Covid-related deaths compared to others.
Kevin McConway
@kjm2
Update: having looked at this a lot more, there does seem to be something odd about the ONS figures for deaths by date of occurrence. Making a plausible adhoc adjustment to allow for this, there are more weeks with excess non-Covid deaths, but still the pattern is quite a lot...
-
Kevin McConway
@kjm2
@Eurostar Hi, I'm In Paris and need to change my return booking to London. I tried to do it on the website but it says I have to call, I guess because it's just changing 1 of 2 passengers. Tried calling, can't get through. Shall I just go to Gare du Nord, or what?
Kevin McConway
@kjm2
OK, I went to Gare du Nord and changed it there, so no further action required, I hope.
-
Kevin McConway
@kjm2
I've been looking at ONS death registration data and at the counts of Covid deaths on the 28-day definition on the dashboard, and noticed something that must have been seen and explained before, but I haven't seen it. Any thoughts? I dare say it's obvious.
1/nPost not available here, view on X
Kevin McConway
@kjm2
...that's not true for 3 periods: right at the start of the pandemic (13-20 March 2020), then from mid-Oct 2020 to mid-Jan 2021, then again recently (from early July 21). Then the ONS figures are still higher (except for 2 weeks), but much less so, generally well under 10%.
4/n
Kevin McConway
@kjm2
These are periods, well, really, the only periods in the data, when deaths were rising fairly fast. So what's the reason? Artefact? Different reporting or certifying behaviour? Any thoughts? @Pouriaaa @BristOliver @d_spiegel @SarahCaul_ONS @Acertaintom
5/5 -
Kevin McConway reposted
David Spiegelhalter
@d_spiegel
Now we are seeing a return to non-Covid health stories, it’s time for press officers, journalists and anyone else to use RealRisk!
realrisk.wintoncentre.uk (with links to our videos) -
Kevin McConway reposted
RSS Data Ethics and Governance Section
@RSS_DatEthGov
It's been announced that implementation of the central GPDPR digital database will be delayed until 1 September. So there's some time to reconsider aspects. We encourage all stakeholders to use this time wisely, so we get a system that benefits patients and is trustworthy.
-
Kevin McConway reposted
RSS Data Ethics and Governance Section
@RSS_DatEthGov
The statistical approach to the 2020 summer exams, and the broader legal and ethical import on the use of comprehensive systems in public administration, is the subject of our next meeting, on Tuesday 8th June, starting at 2:30pm (UK time)
-
Kevin McConway
@kjm2
Definitely of interest to teachers, I'd say. If you can't be there at the start (e.g. because you're teaching) you might still want to tune in for later talks. It's free to RSS e-teacher members.
RSS Data Ethics and Governance Section
@RSS_DatEthGov
On 8 June, 2.30-6.30, meeting on "Statistical accuracy sacrificed to gain public acceptance: Legal, ethical and communication lessons from the UK and Irish 2020 summer exams models", organised by Statistics & Law section and @RSS_DatEthGov. Sign up at rss.org.uk/training-events/events/events-2021/sections/st….
-
Kevin McConway reposted
Lucy 🏳️🌈
@honeypisquared
Please take a look my latest blog in which I think carefully about the work of @mauricechiodo @annemathswatson @mathyawp @DrEugeniaCheng and Paul Ernest. How do you feel about these issues?
CambridgeMathematics
@CambridgeMaths
NEW BLOG: Mathematics as an ethical practice #mathschat #mtbos
www.cambridgemaths.org/blogs/mathematics-as-an-ethical-pr… -
Kevin McConway
@kjm2
I'd say this comes close to scare-mongering, @SkyNews.
news.sky.com/story/covid-19-englands-r-number-could-be-as…
(a) Not news that SAGE say England's R could be as high as 1. The England range is 0.8 to 1.0 unchanged from last week. 1/n
Kevin McConway
@kjm2
(b) It's actually quite good news - 1 is the highest they think it's likely to be so they are saying it's most probably smaller and infections still falling, despite schools reopening etc.
2/3
Kevin McConway
@kjm2
(c) It *is* news that SAGE haven't agreed a UK-wide figure, but they've been saying for a long time that that don't think UK-wide R ranges are very meaningful or helpful.
-
Kevin McConway
@kjm2
Guidance from @d_spiegel and me for statisticians (and others?) engaging with the media on Covid-19 (or anything else) now appearing at rss.onlinelibrary.wiley.com/doi/10.1111/1740-9713.01508. Sound as human as you can, keep off the jargon, realize that it might go wrong, and learn from what went wrong.
-
Kevin McConway reposted
David Spiegelhalter
@d_spiegel
Guidance for any statisticians willing to engage with the media on COVID (and anything else), by @kjm2 and me. rss.onlinelibrary.wiley.com/doi/10.1111/1740-9713.01508 Basically, try and sound human, and be prepared for it all to go wrong
-
Kevin McConway reposted
Office for Statistics Regulation
@StatsRegulation
Thinking of changing career? We are looking people who can apply strong numerical and analytical skills to support our regulatory work.
💰 £36,027
Statistics Regulator: www.civilservicejobs.service.gov.uk/csr/index.cgi?SID=c2V…
Statistics Regulator (Economy) www.civilservicejobs.service.gov.uk/csr/index.cgi?SID=am9… -
Kevin McConway reposted
Anthony Cox
@Cox_A_R
I've written a short piece about the precautionary principle and the AstraZeneca Vaccine issues theconversation.com/blood-clot-fears-how-misapplication-o…
-
Kevin McConway reposted
VeryBritishProblems
@SoVeryBritish
Comp! RETWEET THIS TWEET and one retweeter will win a copy of Born to be Mild and a set of Very British Problems books! (Comp will finish Sunday 21st Feb 2021 at midnight and the winner be chosen at random and informed on the week of Monday 22nd)
www.amazon.co.uk/Rob-Temple/e/B00L3P0OLQ -
Kevin McConway reposted
David Spiegelhalter
@d_spiegel
good analysis refuting misinformation about deaths in 2020 anthonybmasters.medium.com/there-were-over-600-000-death-…
-
Kevin McConway reposted
David Spiegelhalter
@d_spiegel
Great interview with Fiona Fox from the wonderful @SMC_London thebiologist.rsb.org.uk/biologist-covid-19/189-biologist/… (if you didn’t hear it, Nick Robinson ended up asking my opinion on Dominic Cummings, leading to some laughter)
-
Kevin McConway reposted
David Spiegelhalter
@d_spiegel
President of the Royal Statistical Society argues for more embedded experiments to properly evaluate different strategies: proper trials have been essential for treatments and vaccines theconversation.com/vaccine-rollouts-school-testing-and-c…
-
Kevin McConway reposted
Iain Buchan
@profbuchan
Evidence for integrating rapid lateral flow SARS-CoV-2 antigen tests for infectiousness into a comprehensive locally-grounded public health response to #covid19 resilience and recovery: @ScienceShared @Selinarajan @bmj_latest @martinmckee and I explain at www.bmj.com/content/372/bmj.n208.full
-
Kevin McConway
@kjm2
People have been kindly saying that our "Top tips to statisticians", d-spiegel.medium.com/top-tips-to-statisticians-communicat…, makes points that are useful to anyone communicating evidence. But @d_spiegel and I couldn't possibly comment because of our point 2, "Don’t be lured out of your comfort zone"...
-
Kevin McConway
@kjm2
Want to learn from the all the mistakes that @d_spiegel and I have made in communicating statistics? We've
just published our "Top tips to statisticians communicating through the media, especially in the time of COVID-19". link.medium.com/IbDJx9kktdb
Kevin McConway
@kjm2
I could claim that the mistake in the first line of my tweet was put there deliberately to illustrate our point 9, "You’ll get things wrong. Don’t agonise about that." But no, I just made a mistake...
-
Kevin McConway reposted
RSS Data Ethics and Governance Section
@RSS_DatEthGov
As part of our plans for the next few months, we are developing a workshop on teaching ethics for data science students. This is part of the learned societies' work on accreditation of data science courses. If you teach ethics for data science students, please get in touch
-
Kevin McConway reposted
John Burn-Murdoch
@jburnmurdoch
NEW video from me & @tomhannen addressing more myths that have been used to play down Covid this winter.
Featuring:
• Why delays in death registration (& bad charts) wrongly led people to think there was minimal excess mortality
• "Excess winter deaths" are not "excess deaths"
Financial Times
@FinancialTimes
The FT's @jburnmurdoch explains why the UK's Covid-19 death rate is likely to rise further. Watch the full video: www.ft.com/video/0cd6f9f9-664e-40f9-bad4-dde59d7c746c?pla…
This media couldn't be displayed. See it on the original post. -
Kevin McConway
@kjm2
Informative report in journalism.co.uk from @anducnguyen about the symposium he organised in December on coronavirus in the news. He links to a recording of part of it - more at www.youtube.com/channel/UCC8f6WkyIFeYHAiuEltww5w/videos
Prof An Nguyen
@anducnguyen
Excited to see this commentary published www.journalism.co.uk/coronavirus-statistical-chaos-and-th…. Fuller report to follow. @TomChivers @whippletom @JanekirbyPA @PorcelinaD @RossLydall @d_spiegel @flethbridge @JamesFransham @J_CD_T @Sondreus @clairemilleruk @andyextance @RoyalStatSoc @absw
-
Kevin McConway
@kjm2
Excellent thread from Adam on this (which I've only just seen...)
Adam Kucharski
@adamjkucharski
There's been a bit of confusion about the shape of some of the ONS modelled infection estimates, and subsequent updates to the curves - even from people who spend a lot of time looking at COVID data. So what might be doing on? A thread... 1/
-
Kevin McConway reposted
Understanding Patient Data
@Patient_Data
How do people feel about the use of health data? 🤔
There is lots of great research that looks into this.
We've pulled together studies from 2018-2020 to make them easier to access, including work by @OneLondon4 @AdaLovelaceInst @acmedsci @YHCareRecord
understandingpatientdata.org.uk/how-do-people-feel-about-… -
Kevin McConway reposted
Christopher Snowdon
@cjsnowdon
Every time I tweet these stats I get the same old questions and objections in the replies, despite having blocked the worst smileys. So I’ve written out the answers to save time.
-
Kevin McConway reposted
John Burn-Murdoch
@jburnmurdoch
NEW: a common response to reports of hospitals struggling this winter is "it’s no different to a bad flu season!"
I’ve tracked down historical data on flu ICU admissions, including winter 2017-18, a record high.
Here’s how England’s Covid winter compares to a bad flu season 📹 -
Kevin McConway reposted
Theo Sanderson
@theosanderson
PHE has released the underlying data behind the B.1.1.7 technical report, allowing us to see the spread of the new variant in more detail
-
Kevin McConway reposted
The Economist
@TheEconomist
We're looking for an entry-level data-journalism trainee and a data journalist to join The Economist's data team econ.st/38uc71p
-
Kevin McConway
@kjm2
Most demanding statistical analysis of the year, and I didn't even have any chocolates...
-
Kevin McConway reposted
Peter Wells
@peterkwells
I'm organising an event for @RSS_DE_SIG on public sector resource* allocation algorithms** that affect groups of ppl.
Tue 16 Feb 2021, 10am-1pm GMT
Sign up >>
rss.org.uk/training-events/events/events-2021/sections/ex…
* Resources like funds for hospitals or R&D, or where courts & hospital beds are built -
Kevin McConway
@kjm2
Very interesting findings on where people get news about the virus, how this changes, who is trusted. With international comparisons too.
Reuters Institute
@risj_oxford
As the news about a new #covid19 variant hits every country in Europe, it's worth reading this piece by @dragz on what our research says about communications and coronavirus reutersinstitute.politics.ox.ac.uk/risj-review/vaccines-s…
-
Kevin McConway reposted
Nick Stripe
@NickStripe_ONS
THREAD – statistical misrepresentation
I have seen the table below being widely shared to falsely imply that deaths are no higher than normal this year
The table is both factually incorrect and misleading
Those who created it deliberately sow confusion and doubt
1/6 -
Kevin McConway reposted
RSS Data Ethics and Governance Section
@RSS_DatEthGov
Important free conference on statistical chaos in the news run by Bournemouth Univeristy with @RoyalStatSoc on Friday:
www.eventbrite.co.uk/e/coronavirus-statistical-chaos-and-…
Features such luminaries as @kjm2 and @TimandraHarknes (with a cameo from the ubiquitous @d_spiegel - can't stats & media without him) -
David Spiegelhalter
@d_spiegel
ghastly graph from government’s Winter Plan
www.gov.uk/government/publications/covid-19-winter-plan/c… - is this a logarithmic or linear scale?
Kevin McConway
@kjm2
Definitely log. Codged up in Excel, with log scale:
-
Kevin McConway reposted
David Spiegelhalter
@d_spiegel
ghastly graph from government’s Winter Plan
www.gov.uk/government/publications/covid-19-winter-plan/c… - is this a logarithmic or linear scale? -
Kevin McConway
@kjm2
Really important stuff here, in my view.
Alexandra Freeman
@alex_freeman
Some musings from me on risk perception/communication on BMJ blog today.
We throw numbers around when talking about health risks - they’re a way of precisely defining a concept. But it’s like communicating colour through hexademical codes or wavelengths…
blogs.bmj.com/bmj/2020/11/18/alexandra-freeman-the-strang… -
Kevin McConway
@kjm2
Media: worst ever week for Test & Trace; they only reached 59.9% of identified contacts. But the % reached went up this week for contacts managed by local health protection teams AND for contacts not managed by them (What used to be called 'complex' and 'non-complex' cases.) How?
Kevin McConway
@kjm2
It's Simpson's paradox. The % reached is always higher for contacts managed by local HPTs, and the % of contacts dealt with by those teams fell from last week to this, a lot. 3.5% this week, 6.2% last, and until end Sept it was always much higher. assets.publishing.service.gov.uk/government/uploads/syste… table 14
Kevin McConway
@kjm2
But does anyone know why the % (and number) of cases managed by local HPTs has gone down so much? Over 30,000 a week in mid Sept. Last week 11,500. Is it just a delay in reporting or something else?
Kevin McConway
@kjm2
Mind you, in the following week's data (published 12 Nov), they revised the data for that week a bit, though the data file doesn't flag it as revised. It's no longer the worst ever week. They reached 60.2% of contacts, which is tiny bit higher than 60.1% for 2 weeks before that.
Kevin McConway
@kjm2
OK, I know these differences are too small to matter, and they still aren't reaching enough in any case. And it's still Simpson's paradox, because the rate went down overall from the week before to that week, but up in the two pillars separately. Just getting the story straight.
-
Kevin McConway reposted
RSS Data Ethics and Governance Section
@RSS_DatEthGov
The COVID-19 National Core Studies have committed to an admirably broad "set of principles to enable delivery and share data in a way which builds public trust". Challenging but important to take this all on board. See www.hdruk.ac.uk/covid-19/covid-19-national-core-studies/n… @HDR_UK
-
Kevin McConway reposted
Royal Statistical Society
@RoyalStatSoc
We're delighted to be co-hosting this joint symposium with journalists, scientists, statisticians and media scholars discussing the news media's communication of Covid-19 data to the public and the lessons learned so far. Free but registration required: rss.org.uk/training-events/events/events-2020/rss-events/…
-
Kevin McConway reposted
Prof An Nguyen
@anducnguyen
Thrilled to announce "Coronavirus, Statistical Chaos and the News: Preliminary Reflections" - a conference on news reporting of the science and politics behind C19 data and statistics, featuring a stellar group of journalists and academics: www.eventbrite.co.uk/e/coronavirus-statistical-chaos-and-….
-
Kevin McConway reposted
David Spiegelhalter
@d_spiegel
Media asking about why varying estimates of R. 8 groups all estimated UK’s median R on October 8th, from similar data sources, and got non-overlapping intervals. Suggests intervals are too tight - so best to take an individual estimate with caution www.gov.uk/government/publications/spi-m-o-consensus-stat…
-
Kevin McConway reposted
Reuters Institute
@risj_oxford
As the second wave hits the 🇬🇧 UK, 15% of citizens are at risk of being less informed, uninformed or misinformed about #covid19
This is the main takeaway of a new report we publish today, funded by @NuffieldFound
📱Read here
reutersinstitute.politics.ox.ac.uk/communications-coronav…
🧶 Key findings in thread -
Kevin McConway
@kjm2
Excellent piece. And another two recent articles in medical journals about the need to be clear on uncertainty: ebm.bmj.com/content/early/2020/10/18/bmjebm-2020-111541, www.bmj.com/content/371/bmj.m3979 (with subhead "The more certain someone is about covid-19, the less you should trust them".
Stuart Ritchie
@StuartJRitchie
Really enjoyed writing this piece, on COVID-19 and the need to convey uncertainty, with my pal @MWStory! unherd.com/2020/10/how-the-experts-messed-up-on-covid/
Kevin McConway
@kjm2
And doi.org/10.1073/pnas.1913678117 concludes "Results show that whereas people do perceive greater uncertainty when it is communicated, we observed only a small decrease in trust in numbers and trustworthiness of the source, and mostly for verbal uncertainty communication."
-
Kevin McConway reposted
UnHerd
@unherd
It doesn't take a genius to work out why people were put off using the NHS Test and Trace system when they found out the data would be shared with the police | @TimandraHarknes unherd.com/2020/10/public-trust-theres-no-app-for-that/
-
Kevin McConway reposted
Alexandra Freeman
@alex_freeman
Calling all science/health journalists, press officers and those trying to communicate health research:
Delighted to announce the launch of RealRisk, @d_spiegel and the Winton Centre's tool to help you get your numbers across clearly and accurately.
realrisk.wintoncentre.uk -
Kevin McConway reposted
RSS Data Ethics and Governance Section
@RSS_DatEthGov
It is very easy to blame when processes fail, but trustworthy process design is an elaborate investment in quality & standards. There are many operational barriers so @StatsRegulation is doing a review (it's not just about Excel)
Office for Statistics Regulation
@StatsRegulation
The recent error in recording Covid-19 test results highlights the issues in using excel to handle data. Our latest blog advocates for a better way by using a reproducible approach to data analysis that incorporates best practice.
osr.statisticsauthority.gov.uk/now-about-that-excel-sprea… -
Kevin McConway
@kjm2
This looks interesting. This afternoon (14 Oct).
Reuters Institute
@risj_oxford
Today we host a seminar with @safiyanoble, author of the book 'Algorithms of Oppression'. She'll explain what data bias is and why journalists should pay attention to it
🕓 Today at 16:00 UK time
📍 Sign up here us02web.zoom.us/meeting/register/tZwvdOyqpjIrGdMR_4jUVf5L…
🧶 Details on the speaker in this thread -
Kevin McConway reposted
Alexandra Freeman
@alex_freeman
Preprint out – our work on communicating personal risks from COVID-19:
doi.org/10.1101/2020.10.05.20206961
In summary, for those developing personal risk calculators:
1) Are you trying to change behaviour or simply inform people? It changes your communication approach. UK public opinion: -
Kevin McConway reposted
Adam Briggs
@ADMBriggs
15,841 cases from 25/9-02/10 added to the regular daily case updates in 2 days.
Has little implication on how quickly we think cases are rising (use ONS survey/REACT/hospitalisations etc) but the change in positivity rate will emphasise just how strained testing is currently. -
Kevin McConway reposted
RSS Data Ethics and Governance Section
@RSS_DatEthGov
Lying to people is one thing, but what about misleading them?
osr.statisticsauthority.gov.uk/publications/misleadingnes…
@TimandraHarknes talks to Jenny Saul about working with @StatsRegulation and public communication about statistics
rss.onlinelibrary.wiley.com/doi/10.1111/1740-9713.01449
Responsible communication meets reasonable audiences -
Kevin McConway reposted
RSS Data Ethics and Governance Section
@RSS_DatEthGov
Interesting event with Ed Humpherson of @StatsRegulation speaking on the UK approach to commenting on (mis)use of official statistics, and an eminent panel chaired by IAOS President John Pullinger
International Statistical Institute
@Int_Statistical
MISUSE OF STATISTICS: TIME TO SPEAK OUT - Sign up for this #webinar organized by @IAOS_Stat & @IntStat on 6 October 2020, 14.00-16.00 CET. The webinar is free and open to all iaos-isi.org/latestnews/278-misuse-of-statistics-time-to-…
-
Kevin McConway
@kjm2
Interesting, and slightly alarming for the 'health' of news media (though more, 46%, said it hadn't made it either worse or better).
Reuters Institute
@risj_oxford
Most in the UK say news media have helped them respond to #covid19, but 35% say news coverage has made crisis worse, acc. to our new factsheet, #10 from UK COVID-19 news and info project supported by @NuffieldFound
📱Read here
reutersinstitute.politics.ox.ac.uk/most-uk-say-news-media…
🧶Key findings in thread -
Kevin McConway
@kjm2
In case you saw me on @itvnews at 10 yesterday, yes, I did say that to @emilymorganitv about delays between cases in younger people and hospitalisations, but I also told her that it might well not happen here and that we won't necessarily follow Spain. But hey, #editshappen...
Kevin McConway
@kjm2
It wasn't my report - FWIW I'd have been considerably less gloomy (though there are certainly risks). What I (and others) wrote for @SMC_London about yesterday's publications on cases etc at www.sciencemediacentre.org/expert-reaction-to-latest-r-nu…. See also www.sciencemediacentre.org/expert-comments-about-current-… and www.sciencemediacentre.org/expert-reaction-to-latest-nhs-…
-
Kevin McConway
@kjm2
This week @AdaLovelaceInst published a report on building trust in contact tracing apps and similar technology. It's clear, succinct, and I like and agree with its recommendations. www.adalovelaceinstitute.org/wp-content/uploads/2020/08/A…. But I really don't like the way they chose to report it. Why not?
1/11Post not available here, view on X
Kevin McConway
@kjm2
But limitations aren't really mentioned in the @AdaLovelaceInst report, and we aren't told how the findings from the participants were developed into the fine writing in the report, or whether and how the participants were asked about the way their views would be reported.
3/11
Kevin McConway
@kjm2
That matters, because on the front page of the @AdaLovelaceInst website, it says 'The Ada Lovelace Institute is an independent research and deliberative body with a mission to ensure data and AI work for people and society.' Isn't it good practice in reporting research to...
4/11Post not available here, view on X
Kevin McConway
@kjm2
Diversity is just one concern. I'm absolutely not criticising @AdaLovelaceInst, @traversepeople, or the other partners on what they actually did in this deliberation, given the huge restrictions they had to work under, and as I said, I like the recommendations myself.
10/11
Kevin McConway
@kjm2
But I am criticising @AdaLovelaceInst for not mentioning limitations in their report. They do give a link in a footnote to @traversepeople methodology report, but that's not enough. Is their report from a 'research and deliberative body' or from a campaigning organisation?
11/11 -
Kevin McConway
@kjm2
Excellent article that hits all the nails on the head. Read it.
Timandra Harkness
@TimandraHarknes
“That’s the embarrassing truth about algorithms. They are prejudice engines.
Isn’t it strange that we are repelled by prejudice in other contexts, but accept it when it’s automated?”
Me for @unherd on the OfQual Algorithm: unherd.com/2020/08/how-ofqual-failed-the-algorithm-test/ -
Kevin McConway
@kjm2
Just one of a number of interesting new findings from their work on attitudes, beliefs and behaviours during the crisis.
The Policy Institute
@policyatkings
NEW: Large proportions of the UK public say they'd accept big and very long-term changes to how we live, if it becomes clear in the next year or two that a Covid-19 vaccine or treatment can't be produced.
Study with @IpsosMORI
www.kcl.ac.uk/news/how-the-uk-would-be-prepared-to-live-i… -
Kevin McConway reposted
RSS Data Ethics and Governance Section
@RSS_DatEthGov
The current fuss about how to award exam grades has implications for the ethics of data-based systems and algorithms that go beyond exams. An exam system has to be trusted, and trustworthiness applies at different levels - overall grade distribution, risks of disadvantage to...
-
Kevin McConway reposted
RSS Data Ethics and Governance Section
@RSS_DatEthGov
Useful (and short) primer on decision making with uncertainty www.lancaster.ac.uk/staff/diggle/Primer_Uncertainty2.pdf. Makes the points that decisions still need to be made when there's uncertainty, that a decision to wait till there's more evidence may not be right, that decisions may have to change ...
1/n -
Kevin McConway reposted
Reuters Institute
@risj_oxford
1. 57% of Brits think UK government #covid19 response has been worse than other developed countries
This is one of the findings from factsheet #7 of our UK #covidー19 News & Info Project, funded by @NuffieldFound
📱Read it here
reutersinstitute.politics.ox.ac.uk/majority-think-uk-gove…
🧶Key findings in thread -
Kevin McConway
@kjm2
Lots of rather depressing information about Twitter use in this factsheet from @risj_oxford. Worth a read, but it probably won't cheer you up.
Reuters Institute
@risj_oxford
📌 A new factsheet by @silviamajo, @rasmus_kleis, Joan Verdú, @nandanrao, @manlius84 & Omiros Papaspiliopoulos assesses volume/patterns of toxic conversations on social media during the #covid19 pandemic.
📱Read it here
reutersinstitute.politics.ox.ac.uk/volume-and-patterns-to…
🧶Key findings in this thread -
Kevin McConway reposted
Chris Holmes
@cholmesuk
decision theory, causal inference and Bayesian statistics --what more could you want in a paper! -- latest work by Phil Dawid arxiv.org/abs/2004.12493
-
Kevin McConway reposted
Tom King
@Acertaintom
It is time that the big medical magazines remembered their responsibilities, took an extra week (at least) to check consistency, and insisted on PPI where structural inequalities are a factor. The statisticians are getting suspicious:
www.theguardian.com/science/2020/jun/14/scientists-report… -
Kevin McConway reposted
Tom King
@Acertaintom
Interesting recommendations about contact tracing, based on experience of other diseases. But the solidarity aspect of risks and empathy not recognised, and more generally effectiveness of tracing needs more specific evaluation plans
www.newton.ac.uk/event/idp/preprints -
Kevin McConway
@kjm2
I'm still trying to find the best way of explaining what I think is wrong with the Chu et al. paper on distancing etc., in relation to a decision on the right distance limit (www.thelancet.com/journals/lancet/article/PIIS0140-6736(2…). Is the following any clearer?
Post not available here, view on X
Kevin McConway
@kjm2
...'1m' studies give data on the risk of infection if people stay >1m away. So why not just get overall estimates of the risk of staying >2m away and the risk of staying >1m away from those studies? Well, you can do that, and it turns out that the risk of staying >2m away is...
Kevin McConway
@kjm2
...*higher* than the risk of staying >1m away. That clearly makes no intuitive sense, and it happens because the different studies are in very different settings and have very diverse overall rates of infection. So you need a way of putting them on a comparable basis. A...
Post not available here, view on X
Kevin McConway
@kjm2
...the upshot of using a different comparator in the 1m and the 2m studies is that you can't use the results to compare risks with a 1m minimum distance with risks at a 2m minimum distance, because the basis for the comparison has been taken away by using a different divisor...
Kevin McConway
@kjm2
...in calculating the risk ratios - and you can't even guess what the 'right' figure is to divide by in 2m studies, because they give no data on how close people actually got to the source of infection if they went closer than 2m (and how close will differ between studies).
-
Kevin McConway
@kjm2
Thread. 1/n
Intense discussion in the UK about whether minimum physical distance recommendation of 2m should reduce to 1m. The meta-analysis by Chu et al in
@TheLancet
thelancet.com/journals/lancet/article/PIIS0140-6736(20)31… keeps coming up. People quote it as saying the risk at 2m is half the risk at 1m. No.Post not available here, view on X
Kevin McConway
@kjm2
7/n
...despite the inclusion of several more studies than in the preprint. I think something is wrong there. I’ve emailed the authors and @TheLancet about some of these concerns and the authors are considering them.
Kevin McConway
@kjm2
8/8 (ends)
I do agree with @rwjdingwall and others who say that more relevant things have been said by engineers and fluid dynamicists about this issue than observational epidemiology tells us, but the observational epidemiology should be correct and correctly interpreted. -
Kevin McConway
@kjm2
This is a shocking and important story.
Reuters Institute
@risj_oxford
Join our next #risjseminar today at 14:00 UK time.
Investigative journalist @mcaruanagalizia will speak about holding power to account in an event chaired by @MeeraSelva1
📌 Register here
zoom.us/meeting/register/tJwpceutpz0tE9CaOb9QqjYWsy0_XSgf…
🧶 More details about the speaker in this thread -
Kevin McConway reposted
Jonathan Sterne
@jonathanasterne
Our blog on #selectionbias (=#colliderbias) and #covid19 has now been posted by @HDR_UK. Remember - associations with COVID-19 outcomes that are identified in hospitalised patients may not reflect #causaleffects www.hdruk.ac.uk/news/we-should-be-cautious-about-associat… @mendel_random @Garethjgriffith @bristimtom
-
Kevin McConway
@kjm2
Been swapping jobs? @TimandraHarknes @FryRsquared @DameWendyDBE
-
Kevin McConway reposted
Tom Chivers
@TomChivers
This, on the troubles with and limitations of peer review, and how they’ve been thrown into sharp relief by the pandemic and specifically that Lancet hydroxychloroquine study, is fantastic and important by @jamesheathers www.theguardian.com/commentisfree/2020/jun/05/lancet-had-…
-
Kevin McConway reposted
Maarten van Smeden
@MaartenvSmeden
Good call by the Lancet Editors. Medical science has shown its ugly side way too often in the last few months. Ugh
The Lancet
@TheLancet
We have published an Expression of Concern on the paper by Mehra et al on hydroxychloroquine and chloroquine published on May 22, 2020 www.thelancet.com/lancet/article/s0140673620312903
-
Kevin McConway
@kjm2
Decline in trust for politicians and news media down too - but much less change in trust of other institution types. But lots of other interesting things in the @risj_oxford newsletter.
Reuters Institute
@risj_oxford
📬 You've got email!
Our weekly newsletter is out, featuring @dragz @antoniskalog @rasmus_kleis @gijn @ICFJ @silviamajo @sarahsands100 @MeeraSelva1 @NuffieldFound @ReportingHealth and many others
Read it here
mailchi.mp/politics.ox.ac.uk/trust-in-the-uk-government-c… -
Kevin McConway
@kjm2
I think it's excellent that @ONS are looking at #covid19 and its multifarious impacts so broadly, and developing new and modified tools so efficiently. The formal statement on future plans, linked from this blog, is clear and informative.
ONS Focus
@ONSfocus
In today’s blog post, @Liz_McKeown and @GrantFitzner recap the work done so far to uncover new analysis on #covid19 and summarise what the @ONS will be focusing on next. blog.ons.gov.uk/2020/06/01/informing-the-pandemic-respons…
-
Kevin McConway reposted
Trish Groves
@trished
@mendel_random @d_spiegel @bmj_latest propose stratified shielding thru “chance of getting infected” score based on current local #covid-19 infection levels + “risk of dying if infected” score depending on personal risk factors www.bmj.com/content/369/bmj.m2063
-
Kevin McConway reposted
Sander Greenland
@Lester_Domes
Also: commitment to past conclusions, advice, and preferred experts. See eg endnote at www.bild.de/politik/inland/politik-inland/fragwuerdige-me… -may explain why, despite first finding a "stat sig" difference, they buried it by doing more comparisons (AKA upward-P hacking) medium.com/@d_spiegel/is-sars-cov-2-viral-load-lower-in-y… @kjm2 @d_spiegel
-
Kevin McConway reposted
David Spiegelhalter
@d_spiegel
Thanks, I do know what a preprint server is. And this is not on one. So it needs to be withdrawn from the website, and replaced by a new paper - apparently this is going to happen. But still should be on a proper preprint server.
-
Kevin McConway reposted
Timandra Harkness
@TimandraHarknes
I do think contact-tracing is an important part of both reducing spread and protecting the more vulnerable from Covid-19. I also think it's better done by humans (though a well-designed app could supplement it).
But ....
1/2
www.bbc.co.uk/news/uk-52829357 -
Kevin McConway
@kjm2
Claims that children with COVID are as infectious as adults are often based on zoonosen.charite.de/fileadmin/user_upload/microsites/m_cc… . But their data suggest there *is* a difference in viral load of children and adults medium.com/@d_spiegel/is-sars-cov-2-viral-load-lower-in-y…. @kjm2 and @D_Spiegel recommend that the pre-print is withdrawn.
Kevin McConway
@kjm2
More details in @d_spiegel thread at x.com/d_spiegel/status/1265167482450522124. The statistical analysis in the preprint is inappropriate. Important to point out that the authors, rightly, didn't actually say that children *are* as infectious as adults anyway.
David Spiegelhalter
@d_spiegel
Is SARS-CoV-2 viral load lower in young children than adults? Jones et al virologie-ccm.charite.de/fileadmin/user_upload/microsites… claim no evidence for this, but their statistical analysis is inappropriate. @kjm2 and @d_spiegel recommend the pre-print is withdrawn medium.com/@d_spiegel/is-sars-cov-2-viral-load-lower-in-y…
Kevin McConway
@kjm2
@kjm2 and @d_spiegel wish to distance themselves from newspaper attacks on @c_drosten and his group. We understand that the group is continuing to work on viral load, and will make the statistical and medical position clearer. We cannot comment on the non-statistical aspects.
-
Kevin McConway reposted
RSS Data Ethics and Governance Section
@RSS_DatEthGov
@Acertaintom has posted a thoughtful blog about ethics in a time of SARS 2. Many important issues raised and discussed, including what makes some of the ethical questions rather different from what's commonly been considered before. publicstatistic.wordpress.com/2020/05/13/ethics-in-a-time…
-
Kevin McConway
@kjm2
Many good articles about COVID-19 & other subjects from @ConversationUK . This one reports survey findings on public understanding of, and feelings about, statistical messages in the media. Not very encouraging. How can we do this better & promote trust? theconversation.com/coronavirus-public-confused-and-suspi…
-
Kevin McConway
@kjm2
(Nerdy statistician point) Isn't there a misdescription of a confidence interval meaning in today's @ONS report on infection? Summary says "It is estimated that an average of 148,000 people in England had COVID-19 during this time (95% confidence interval: 94,000 to 222,000). But
Post not available here, view on X
Kevin McConway
@kjm2
Anyway, I see they've changed the explanation in this week's release www.ons.gov.uk/peoplepopulationandcommunity/healthandsoci… to (drum roll)...
Kevin McConway
@kjm2
... "The 95% confidence intervals are calculated so that, if we were to repeat this study many times, with many different samples of households, then 95% of the time the confidence intervals would contain the true value that we are seeking to estimate."
-
Kevin McConway reposted
RSS Data Ethics and Governance Section
@RSS_DatEthGov
This new US article on ethical and legal aspects of the
@seattleflustudy, academic.oup.com/jlb/advance-article/doi/10.1093/jlb/lsaa…
discusses the use of research data for public health purposes not explicitly discussed with the research participants. Maybe the balance of rights wouldn't be the same with GDPR. -
Kevin McConway
@kjm2
More really interesting stuff from @risj_oxford.
Reuters Institute
@risj_oxford
1. Initial surge in news use around coronavirus in 🇬🇧 has been followed by significant increase in #newsavoidance
Here's a key finding of factsheet #3 of our UK #covidー19 News & Information Proj, funded by @NuffieldFound
📱Read it here
reutersinstitute.politics.ox.ac.uk/initial-surge-news-use…
🧶 More in thread -
Kevin McConway
@kjm2
Yet more interesting webinars at @risj_oxford this week. Wednesday, @cjimenezcruz on fact checking a global story, Thursday, Denise Lievesley presents a guide to statistics for journalists. reutersinstitute.politics.ox.ac.uk/calendar
-
Kevin McConway reposted
Reuters Institute
@risj_oxford
Here's a thread with great #datajournalism on #covid19. Please share and feel free to add suggestions at the end
1. 🇪🇸 As Spanish national government wasn't giving data on the # of tests, nonprofit @civio started to build its own dataset (in Spanish)
datos.civio.es/dataset/pcr-coronavirus-covid19-espana-com… -
Kevin McConway reposted
RSS Data Ethics and Governance Section
@RSS_DatEthGov
This is good news.
@AdaLovelaceInst
has been a leader in the move from concentrating on technical and governance aspects of data to engaging the public in wide consideration of transformative impacts on society, and the appointment of
@DameWendyDBE
will strengthen that.
Ada Lovelace Institute
@AdaLovelaceInst
We are delighted to welcome our new chair @DameWendyDBE, appointed by our founder @NuffieldFound.
'Dame Wendy will deepen @AdaLovelaceInst expertise in data science & build connections across academia, government & industry.' said Director @carlykind_
www.adalovelaceinstitute.org/professor-dame-wendy-hall-ap… -
Kevin McConway reposted
David Spiegelhalter
@d_spiegel
My blog on the COVID risks faced by *population* during the peak of the epidemic (great ONS E+W data)
medium.com/@d_spiegel/what-are-the-risks-of-covid-and-wha… 1 in 1800 died over 5 weeks. Risks doubled if a man, and for each 6–7 years extra age: compared to 20-year-old, an 80-year-old had ~ 500 times risk -
Kevin McConway
@kjm2
Many interesting things here from @risj_oxford . Seminar tomorrow (14th) from @dragz on their research on polarised attitudes towards COVID-19 news coverage (etc.), research job on trust in news, research on expert and public views on accuracy and trust in media in 23 countries.
Reuters Institute
@risj_oxford
📬 you've got email!
Our weekly newsletter is out, featuring @annisch @dragz @marina_popescu @MeeraSelva1 @dorotheabyrne @apoorva_nyc @mtosterholm @miamalan @dayoaiyetan @hotzthoughts @xhgMattia and others
📱Read it here mailchi.mp/politics.ox.ac.uk/do-experts-and-the-public-ra… -
Kevin McConway
@kjm2
Definitely worth a read on the issues of using observational data to think about causes.
-
Kevin McConway reposted
David Spiegelhalter
@d_spiegel
Polite request to PM and others: please stop using my Guardian article to claim we cannot make any international comparisons yet. I refer only to detailed league tables-of course we should now use other countries to try and learn why our numbers are high www.theguardian.com/commentisfree/2020/apr/30/coronavirus…
-
Kevin McConway
@kjm2
Some extraordinarily polarised views on how good a job the UK Government is doing in responding to the pandemic, as revealed in new research for @risj_oxford reutersinstitute.politics.ox.ac.uk/news-media-broadly-tru…. Plenty of other interesting things in there too.
Kevin McConway
@kjm2
More from @risj_oxford, with more detail about the polarisation, public opinion on how UK govt is doing compared to other countries, and more, in this week's factsheet at reutersinstitute.politics.ox.ac.uk/UK-public-opinion-pola…
-
Kevin McConway reposted
Reuters Institute
@risj_oxford
Asked to compare the UK gov’s response to most other developed countries, almost half (46%) of our respondents say it's been worse and only 12% say it's been better.
📱Read the new factsheet of our UK #covid19 news and information project
reutersinstitute.politics.ox.ac.uk/UK-public-opinion-pola… -
Kevin McConway reposted
Matt Singh
@MattSingh_
🚨Case study in the ecological fallacy: Local authorities in England and Wales with more over-65s have LOWER #covid19 death rates. If you only looked at this data, you might think it killed more young people. But we have robust individual level data, so we know it's the reverse.
-
Kevin McConway reposted
RSS Data Ethics and Governance Section
@RSS_DatEthGov
This, assuming it's reasonably valid, may have consequences for engagement of the public in relation to decisions about policies and actions on coronavirus. Full report at www.kcl.ac.uk/policy-institute/assets/Coronavirus-in-the-… , and statisticians may want to read the technical details page near the end.
The Policy Institute
@policyatkings
NEW STUDY: Analysis reveals the UK is made up of three broad but distinct groups of people responding to the coronavirus crisis and lockdown in different ways:
🟣The Accepting (48% of UK)
🔵The Suffering (44%)
🟠The Resisting (9%)
www.kcl.ac.uk/news/the-three-groups-reacting-to-life-unde… -
Kevin McConway reposted
RSS Data Ethics and Governance Section
@RSS_DatEthGov
...uk.reuters.com/article/uk-health-coronavirus-europe-tech/……. And what should the legal background be? Academics have proposed a law giving safeguards, at osf.io/preprints/lawarxiv/yc6xu/. Likely to come up at @CommonsSTC tomorrow, 9:30-11:30.
What do you think and feel about this?
4/4 -
Kevin McConway reposted
RSS Data Ethics and Governance Section
@RSS_DatEthGov
As @AdaLovelaceInst say, this should be only the start of public discussion about using tech to tackle Covid. Issues of accountability, privacy, our rights, but also practicability: how many people need to use an app, how many have the right phones and will use it correctly?
2/4 -
Kevin McConway reposted
RSS Data Ethics and Governance Section
@RSS_DatEthGov
Many aspects discussed by @TimandraHarknes at unherd.com/2020/04/can-your-smartphone-crack-covid/, but position changing fast. One issue is whether the system is centralised so health authorities control tracing data, or decentralised so users have more control. Germany just changed track, see:...
3/4 -
Kevin McConway reposted
RSS Data Ethics and Governance Section
@RSS_DatEthGov
Tomorrow 27/4, @CommonsSTC evidence session for its inquiry on research and tech in global disease outbreaks: committees.parliament.uk/event/837/formal-meeting-oral-ev…. Will consider legal and ethical aspects of apps for contact tracing. Good discussion of this by @AdaLovelaceInst at www.adalovelaceinstitute.org/our-work/covid-19/covid-19-e….
1/4 -
Kevin McConway reposted
Tom King
@Acertaintom
The view is vaccine comes next year, so we could spend that time developing public information and engagement programmes, documenting how vaccines work and how they are developed. A vaccine is no good if rejection compromises herd immunity
www.theguardian.com/world/2020/apr/21/anti-vaccination-co… -
Kevin McConway
@kjm2
Some interesting and thoughtful analysis about coronavirus from @policyatkings. Including from some people that we once heard from a lot but don't so much now. E.g. Charles Clarke on mass testing, tracing and individual rights www.kcl.ac.uk/news/mass-coronavirus-testing-and-tracing-p… ...
Kevin McConway
@kjm2
… and from the much less strident Johnson brother
@JoJohnsonUK
on higher education after the virus. Will my erstwhile employer
@OpenUniversity
do differently, and if so how, I ask myself? www.kcl.ac.uk/news/what-will-higher-education-look-like-a… -
Kevin McConway
@kjm2
📌 NEW REPORT: Some very interesting stuff from @risj_oxford on how people in different countries get their news on COVID-19: mailchi.mp/politics.ox.ac.uk/new-report-how-people-get-th…
-
Kevin McConway
@kjm2
I'm so sorry to hear this. An outstanding scholar, influential, friendly, supportive.
-
Kevin McConway reposted
David Spiegelhalter
@d_spiegel
excellent discussion of death reporting from CEBM Oxford www.cebm.net/covid-19/reconciling-covid-19-death-data-in-…
-
Kevin McConway
@kjm2
This report on misinformation about COVID-19 is very interesting. Please read the whole @risj_oxford thread on this, and also the factsheet itself.
Reuters Institute
@risj_oxford
📌 What are he main formats, sources, and claims of #covid19 misinformation? How have platforms responded?
A new piece of research by @jsbrennen @_FelixSimon_ @pnhoward & @rasmus_kleis analyses 225 fact-checks.
📱Full factsheet here
reutersinstitute.politics.ox.ac.uk/types-sources-and-clai…
🧶Key findings here -
Kevin McConway
@kjm2
'Heart-breaking that cuts to journalism come at a time when it is needed more than ever.' www.pressgazette.co.uk/science-media-centre-chief-heart-b…
-
Kevin McConway reposted
Nigel Marriott
@MarriottNigel
When it comes to #coronavirus reporting, which individual journalist has impressed you the most so far?
I want to mention Paul Nuki from the Daily Telegraph. His #covid19 articles have been excellent. Here is his latest.
www.telegraph.co.uk/global-health/science-and-disease/cor… -
Kevin McConway reposted
Aidan Peppin
@AidanPeppin
I know how people love flowacharts so I made one
#dataethics #covid19 -
Kevin McConway
@kjm2
The UK Govt daily briefings give hospital admissions from COVID-19 in England, see www.gov.uk/government/publications/slides-and-datasets-to… . But source given only as NHS, and the numbers each day are far bigger than the new case counts for UK. Why? Where the data are from? @robertcuffe @PHE_uk @NHSDigital
-
Kevin McConway reposted
David Spiegelhalter
@d_spiegel
excellent stats coverage from @robertcuffe and @chrisjeavans at BBC www.bbc.co.uk/news/health-52133054
-
Kevin McConway reposted
David Spiegelhalter
@d_spiegel
Congratulations to @UKStatsAuth, @StatsRegulation, @ONS, @NHSuk, @PHE_uk, @DHSCgovuk for improvements in Covid mortality stats. UKSA and OSR have been pushing hard www.statisticsauthority.gov.uk/news/statement-from-the-of… DHSC now clear that daily counts are in-hospital only and delayed www.gov.uk/guidance/coronavirus-covid-19-information-for-…
-
Kevin McConway reposted
David Spiegelhalter
@d_spiegel
My blog suggesting that getting COVID-19 is, rather remarkably, like packing a year’s worth of risk into a week or two
medium.com/wintoncentre/how-much-normal-risk-does-covid-r… -
Kevin McConway reposted
David Spiegelhalter
@d_spiegel
Thoughtful blog from Michael Blastland on expert disagreement and tolerance of uncertainty medium.com/wintoncentre/quick-thoughts-on-coronavirus-and…
-
Kevin McConway reposted
Paul Mason
@paulmasonnews
Please help researchers at @Imperial_PERC - looking for people to help shape #covid_19 research priorities and plans. Form takes 10 mins to complete and could help inspire new ways to work with communities during a public health emergency imperial.eu.qualtrics.com/jfe/form/SV_7PbGOlNk5W3ecF7
Closes 15/03/20 -
Kevin McConway
@kjm2
Contains some links to excellent level-headed advice about how to report on the coronavirus outbreak.
Reuters Institute
@risj_oxford
📬 You've got email!
Our weekly newsletter is out, featuring @ilpost @zseward @maldita_es @MeeraSelva1 @simgandi @rasmus_kleis @AlexaBorchardt @dorotheabyrne @atompkins @firstdraftnews @SiouxsieW @XTOTL @EvanMPeck @CarolineYLChen
Read here
mailchi.mp/politics.ox.ac.uk/how-to-cover-coronavirus-fem… -
Kevin McConway
@kjm2
Title page verso, front and back cover of a book I've just bought. But does this mean that I shouldn't believe a word of it? Device to ward off litigation, or false advertising on the cover? @HoZ_Books @DanaThomasParis
-
Kevin McConway reposted
David Spiegelhalter
@d_spiegel
My take on communicating about coronavirus: medium.com/wintoncentre/communication-about-coronavirus-c…
-
Kevin McConway reposted
David Spiegelhalter
@d_spiegel
@kjm2 and I on misuse of live facial recognition stats: "When looking for a needle in a haystack, even for the sharp-eyed, there’s a lot of bits of straw that look like needles” medium.com/wintoncentre/live-facial-recognition-how-good-…
-
Kevin McConway reposted
Randi (Cohen) Slack
@randicohen89
To celebrate the publication of the latest book in our #datascience book series, JavaScript for Data Science, I am giving away a free copy. To win, follow me and retweet this message. I will pick a winner at the end of this week. #javascriptgiveaway @gvwilson @Mayacelium @tbyhdgs
-
Kevin McConway
@kjm2
Live facial recognition: you need more than one number to talk about its accuracy. @d_spiegel and I explain, with examples from @UKHouseofLords, @BBCNews, @CDEIUK etc.
medium.com/wintoncentre/live-facial-recognition-how-good-… -
Kevin McConway reposted
David Spiegelhalter
@d_spiegel
Should live facial recognition be described as ’80% accurate’? @kjm2 and I take apart the stats
medium.com/wintoncentre/live-facial-recognition-how-good-… -
Kevin McConway reposted
RSS Data Ethics and Governance Section
@RSS_DatEthGov
The @d_spiegel paper 'should we trust algorithms?' is published by Harvard Data Science Review: hdsr.mitpress.mit.edu/pub/56lnenzj
Structured openness for the evidence around F R as decision support is indicated, and the phases offer a template -
Kevin McConway reposted
RSS Data Ethics and Governance Section
@RSS_DatEthGov
Jane Hutton has contested the professional ethics in the USS pension scheme
www.statslife.org.uk/news/4362-rss-fellow-jane-hutton-com… -
Kevin McConway
@kjm2
1/n
I think there are some important (or at least interesting) ethical aspects of those new guidelines about red and processed meat that came out today. First, they are explicitly said to be clinical guidelines, aimed at individuals who eat meat.Post not available here, view on X
Kevin McConway
@kjm2
4/n
...even if in the view of the reviewers (and I mostly agree) the size of the change in risk if you cut down on the meat is pretty small, is it right to recommend that clinicians should suggest to all their adult patients that they should continue to eat the current amounts...
Kevin McConway
@kjm2
5/n
...of both processed and unprocessed red meat, rather than trying to get the size of the risk and the strength of the evidence across and letting the patients decide (which, in the end, the patients will do anyway)? For public health there has to be a general statement,...Post not available here, view on X
Kevin McConway
@kjm2
8/n
Or not? If so, how? Should your doctor say "The risks aren’t huge, and anyway most people don’t want to change their consumption level, so you shouldn’t", even if you personally would be perfectly happy to change your consumption?
Kevin McConway
@kjm2
9/9 (ends)
Is this more medical paternalism, or is it what people want to happen? (Or both perhaps?) -
Kevin McConway reposted
David Spiegelhalter
@d_spiegel
fine (free) article 'How to communicate evidence to patients’ dtb.bmj.com/content/57/8/119
COI: by my excellent colleague, Alex Freeman -
Kevin McConway reposted
Kirsty Lang
@thatkirstylang
Are sugary drinks causing cancer?@JustinOnWeb on @BBCr4today absolutely right to point out how the reporting of “relative risk” v “absolute risk” distorts our understanding of risks around #cancer. www.bbc.co.uk/news/health-48939671
-
Kevin McConway
@kjm2
Great day at #cijsummer, partly because I got the opportunity to talk to journalists about study design and how to read scientific papers, but mainly because what the journalists talk about is so interesting and important.
-
Kevin McConway
@kjm2
Great to be in Newcastle again, if only for a couple of days. Here partly for @RSS_DE_SIG meeting on data governance.
-
Kevin McConway reposted
RSS Data Ethics and Governance Section
@RSS_DatEthGov
Planning a meeting on 'characteristics of good data governance' in Newcastle, in May. Get in touch if you have suggestions of contributors
-
Kevin McConway reposted
UK Statistics Authority
@UKStatsAuth
Ed Humpherson, DG Regulation welcomes @UKStatsAuth guest blog uksa.statisticsauthority.gov.uk by Madeleine Murtagh and Thomas King on more to data governance than legal compliance @RSS_DE_SIG
-
Kevin McConway reposted
RSS Data Ethics and Governance Section
@RSS_DatEthGov
Next week we hold our first event - on the #dataethics landscape. We need #rssfellows to come and talk about #dataethics @RoyalStatSoc
www.statslife.org.uk/events/events-calendar/eventdetail/1… -
Kevin McConway
@kjm2
Ooh! Condorcet! Intransitive preferences! www.deltapoll.co.uk/steve-fisher-condorcet
Kevin McConway
@kjm2
Or maybe not, see x.com/AaronBell80/status/1067790011972620288
-
Kevin McConway reposted
Royal Statistical Society
@RoyalStatSoc
RSS VP for Academic Affairs, Guy Nason, has written an editorial in our Series A journal on statistical flaws in the teaching excellence and student outcomes framework. It's currently open access for the next few days for anyone wishing to read it. #tef rss.onlinelibrary.wiley.com/doi/full/10.1111/rssa.12403
-
Kevin McConway reposted
RSS Data Ethics and Governance Section
@RSS_DatEthGov
We have been mapping the landscape on #dataethics - #rssfellow please can you help us understand #dataethics bodies around the world:
www.statslife.org.uk/members-area/latest-call-outs-to-mem… -
Kevin McConway reposted
Samuel Schumacher
@sgschumacher
I knew publication bias can be pretty bad but this is insane
-
Kevin McConway reposted
Tom King
@Acertaintom
No board, no response to public consultation, yet the @hmtreasury is already telling the CDEI what to do
www.gov.uk/government/publications/budget-2018-documents
@RSS_DE_SIG warned that independence would be critical to maintaining public confidence and so far the CDEI does not deserve that -
Kevin McConway reposted
Rob Eastaway
@robeastaway
How to lie with statistics #53: The DfE is shamelessly pinning this graph showing increased spending on schools.
(1) note the scale on the left starts at £36bn, not zero.
(2) no mention that the number of students has grown at a similar rate
(3) inflation is ignored. -
Kevin McConway reposted
David Spiegelhalter
@d_spiegel
shocking that alcohol paper www.thelancet.com/journals/lancet/article/PIIS0140-6736(1… broke Lancet guidelines in only reporting relative risks: needed fine press office to extract absolute risks from them
medium.com/wintoncentre/the-risks-of-alcohol-again-2ae8cb… -
Kevin McConway reposted
Anna Berry
@Weeannabee
Come and hear the fascinating @jasonhickel talk about degrowth in #miltonkeynes! @thisistotalmk @_MiltonKeynes @WhereInMK @MiltonKeynes_MK @mkfuturenow
Jason Hickel
@jasonhickel
On Sept 20 I'll be in Milton Keynes to talk about #degrowth and other fun ideas at the unveiling of a new work by the brilliant artist Anna Berry. Come join us! www.eventbrite.co.uk/e/the-constantly-moving-happiness-ma…
-
Kevin McConway reposted
Jason Hickel
@jasonhickel
On Sept 20 I'll be in Milton Keynes to talk about #degrowth and other fun ideas at the unveiling of a new work by the brilliant artist Anna Berry. Come join us! www.eventbrite.co.uk/e/the-constantly-moving-happiness-ma…
-
Kevin McConway
@kjm2
Indeed very funny, but also pretty informative.
Daniël Lakens
@lakens
Very funny talk by @MikeKSmith about the alpha wars and p-values: youtu.be/snoeQYR1ErQ?t=10m10s "To me, this [redefining statistical significance] is like a Jar-Jar Binks argument: It might seem like a good idea when you first propose it...." #justifyalpha
-
Kevin McConway reposted
Sense about Science
@senseaboutsci
'Textbook cherry-picking,' an implausible mechanism of action and a conspiracy theory that doesn't stand up, all in @drg1985's expert take down of @guardian's piece linking mobile phones and cancer www.theguardian.com/technology/2018/jul/21/mobile-phones-…
-
Kevin McConway reposted
RSS Data Ethics and Governance Section
@RSS_DatEthGov
David Spiegelhalter @RoyalStatSoc President is giving a Turing Lecture on 11 December, offering the Predict system as an exemplar of algorithmic explainability
www.turing.ac.uk/events/turing-lecture-be-prepared-show-y… -
Kevin McConway
@kjm2
Excellent thought-provoking installation by @Weeannabee, mkfestivalfringe.com/events/paradise-lost/. Milton Keynes City Centre, in the big underpass near MK Gallery and MK Theatre going towards Campbell Park. It's only there till 6 today, go if you possibly can, but then at @MKMuseum 15-19 July.
-
Kevin McConway
@kjm2
Good to see @_datatree safely launched, and happy to have played a small part.
-
Kevin McConway reposted
Timandra Harkness
@TimandraHarknes
I'm recording interviews for my new @BBCRadio4 series, How To Disagree.
So far, interviewees have argued with the premise of the questions, asked me harder questions back, and disagreed with me about the premise of the whole series.
I'm very happy. -
Kevin McConway reposted
HealthNewsReview
@HealthNewsRevu
Reporting the findings: Absolute vs relative risk www.healthnewsreview.org/toolkit/tips-for-understanding-s…
-
Kevin McConway
@kjm2
TLS maybe not the obvious place for an article on statistics, but do read www.the-tls.co.uk/articles/public/thomas-bayes-science-cr… (If you're new to this, you should know that these views are still heavily contested, though mostly not by me.)
-
Kevin McConway
@kjm2
Really rewarding teaching journalists about statistics and scientific methods at #cijsummer. They can see the need for it and ask great questions.
-
Kevin McConway reposted
Hetan Shah
@HetanShah
Sometimes the problem is not a lack of evidence but that we don’t make it usable, or simply that we don’t use it @TimHarford www.ft.com/content/c341e146-52af-11e8-b3ee-41e0209208ec
-
Kevin McConway
@kjm2
@johnlewisretail Here is a chair in the café at the front of John Lewis Milton Keynes. The ends of the arms of all the chairs seem to be like that. Why?
Kevin McConway
@kjm2
@johnlewisretail Floor none too clean either.
-
Kevin McConway reposted
Stephen John Senn
@stephensenn
My latest blog on randomisation errorstatistics.com/2018/01/13/s-senn-being-a-statisticia…. My thanks to @learnfromerror for hosting it and to @trishgreenhalgh for alerting me to the paper by Deaton and Cartwright
-
Kevin McConway reposted
Tom Chivers
@TomChivers
21 of the most extraordinary science photos of 2017 www.buzzfeed.com/tomchivers/look-at-the-little-squid
-
Kevin McConway reposted
JP Willans
@Joelwillans
Who says Germans don't have a sense of humour?
-
Kevin McConway reposted
CRC Press Data Science, Stats, and Math Books
@CRC_MathStats
COMPETITION! Win £100 of books. All you need to do is like & retweet this tweet & make sure you follow us! T&C's: www.routledge.com/go/crc_mathematics_statistics_twitter_c…
-
Kevin McConway reposted
Prof. Jennifer Visser-Rogers
@StatsJen
@RoyalStatSoc is looking for nominations for the #statoftheyear…what’s yours? www.rss.org.uk/statoftheyear
-
Kevin McConway reposted
David Spiegelhalter
@d_spiegel
BBC Trust report on statistics says avoid false balance and challenge faulty stats on the spot: @BBCr4today failed with Lawson
-
Kevin McConway reposted
FAZ Wirtschaft
@FAZ_Wirtschaft
„Kühe sind gefährlicher als Autos“. Ein interview mit Gerd Gigerenzer, Direktor am Max-Planck-Institut www.faz.net/aktuell/wirtschaft/diesel-affaere/risikoforsc…
-
Kevin McConway reposted
Stephen John Senn
@stephensenn
How a public hangman understood a fact about modelling the EBM movement doesn't errorstatistics.com/2013/04/19/stephen-senn-when-relevanc…
-
Kevin McConway reposted
Stuart
@TheBigBlether
Whenever I see a headline like 'Coffee makes you live longer' I await a response from Prof McConway @kjm2 #coffee
-
Kevin McConway
@kjm2
2/2 It is like saying, 'My mother, drunk or sober'. GK Chesterton, A Defence of Patriotism, www.online-literature.com/chesterton/the-defendant/16/
-
Kevin McConway
@kjm2
1/2 'My country, right or wrong' is a thing that no patriot would think of saying, except in a desperate case.
BBC Newsnight
@BBCNewsnight
“It would be helpful if broadcasters were willing to be a bit patriotic” - @andrealeadsom tells @maitlis after being questioned on Brexit
-
Kevin McConway reposted
David Spiegelhalter
@d_spiegel
Great RSS meeting on stats and media in Leeds next Wednesday - register here www.eventbrite.co.uk/e/afternoon-meeting-statistics-the-m…
-
Kevin McConway reposted
Royal Statistical Society
@RoyalStatSoc
Our event with @britac_news on elections in a fakenews era with @meganlucero, @d_spiegel, @hetanshah & more www.britac.ac.uk/events/has-post-truth-era-killed-our-cha…
-
Kevin McConway reposted
Quorum MK
@QuorumMk
Concert next Sat 8th - see poster! Awesome programme...Victoria, Taverner, Byrd...performed by Quorum
#choralmusic -
Post not available here, view on XPost not available here, view on X
Kevin McConway
@kjm2
It is indeed from the same talk, by me, but the slide is based on a study done at @PsychCardiffUni, lead author Rachel Adams @scottmkeir
-
Post not available here, view on X
Kevin McConway
@kjm2
.@Pri_Mis @Stempra and to give credit where it's due, this is based on empirical work at @PsychCardiffUni
-
Kevin McConway reposted
Scott Keir
@scottmkeir
Good day in Cambridge, meeting with @alex_freeman @d_spiegel @kjm2 to discuss #statisticalliteracy. New project coming together, exciting.
-
Kevin McConway reposted
David Spiegelhalter
@d_spiegel
Daily Mail’s own special way of showing a change from 0.6% to 0.7% www.dailymail.co.uk/news/article-4248690/Economy-grew-0-7…
-
Kevin McConway
@kjm2
Re #vitamin meta-analysis in @bmj_latest , paper and authors' response to editorial refer heavily to supplementary material. Where is it?
-
Kevin McConway reposted
Rory Cellan-Jones
@ruskin147
www.bbc.co.uk/programmes/p04slydb ..and by the way hard to think of a programme more central to the BBC's mission right now than More or Less
-
Kevin McConway reposted
Information is Beautiful
@infobeautiful
Clever dataset analysis by @upshotnyt suggests Trump's polling success may be down to one 19-yr-old Illinois man: www.nytimes.com/2016/10/13/upshot/how-one-19-year-old-ill…
-
Kevin McConway reposted
Richard Armitage
@RichardArmitag3
All you need is PLoveDiv plus @BGWineTours clever programmes & fab wines. Try it - you'll PLove it!
-
Kevin McConway reposted
Guardian news
@guardiannews
Martin stars but Deledio injured as Richmond edge past Bombers in AFL ebx.sh/2a5xT0K
-
Kevin McConway reposted
Prof. Jennifer Visser-Rogers
@StatsJen
Surely soon I'll wake up and I won't be in a world where we voted to leave the EU and then Boris Johnson became foreign secretary
-
Kevin McConway reposted
Doug Clow
@dougclow
Fun problem: Have caught N taxis from a firm w/o getting same one, estimate nr of cabs firm has. Capture-recapture not quite right sums.
-
Kevin McConway
@kjm2
OK, just retired from Open University after 35 interesting years. Offers of lucrative sinecures obviously seriously considered.
-
Kevin McConway reposted
Matt Goodwin
@GoodwinMJ
New research suggests why general election polls were so inaccurate www.theguardian.com/politics/2015/nov/13/new-research-gen…
-
Kevin McConway reposted
Coronation Street
@itvcorrie
To celebrate World Statistics Day we've been doing some number crunching! #corrie #statsday15
-
Kevin McConway reposted
生活雑貨・⭐
@Paul_vanderLaan
John Pullinger (UK National Statistician): Why World Statistics Day is something worth celebrating - gu.com/p/4de4c/stw. #statsday15
-
Post not available here, view on X
Kevin McConway
@kjm2
@NRE_LondonMid Lots of us have been on train on platform 8at Euston for 40 mins, no announcements. What's happening? Tell us.
-
Kevin McConway reposted
Ian Katz
@iankatz1000
Here's reminder of @johnmcdonnellMP telling @EvanHD why Lab would vote FOR fiscal responsibility charter (at 9'50'') youtu.be/9keoMALBzwc
-
Kevin McConway reposted
Peter Aldhous
@paldhous
What probability means, in different professions
mathwithbaddrawings.com/2015/09/23/what-does-probability-… -
Kevin McConway reposted
Emerging Apps
@EAS_RSS
The amazing line up of speakers is @d_spiegel, @FryRsquared, @kjm2, @Smyth_Chris and @anthony_reuben goo.gl/loKkBv
-
Kevin McConway reposted
Emerging Apps
@EAS_RSS
We have a fantastic free event on Stats in the Media coming up at @RoyalStatSoc in London on the evening of 9th June goo.gl/loKkBv
-
Kevin McConway reposted
Hetan Shah
@HetanShah
Learn for free from the experts how to communicate data & stats to the media - @FryRsquared @d_spiegel @kjm2 -www.statslife.org.uk/events/events-calendar/eventdetail/4…
-
Kevin McConway
@kjm2
By me, just in case you've not had enough of them...Explainer: how do you read an election poll? theconversation.com/explainer-how-do-you-read-an-election… @ConversationUK
-
Kevin McConway reposted
The Guardian
@guardian
Australia condemns killing of dolphins and seals by factory fishing trawler www.theguardian.com/environment/2015/may/03/australia-con…
-
Kevin McConway
@kjm2
Voiced by me:
Catherine Chambers
@Catherine_C
Opinion Polls in A Nutshell - short comedic animations on polls, exit polls and predictions #election2015 www.youtube.com/playlist?list=PLhQpDGfX5e7DKIcSVHcrk3R3Yu…
-
Kevin McConway reposted
Hetan Shah
@HetanShah
Aircraft accident rates at historic low despite high-profile plane crashes gu.com/p/44fb6
-
Kevin McConway reposted
Hetan Shah
@HetanShah
Fact Check Central: Good to see one place to look at all fact checks factcheckcentral.org @senseaboutsci @FullFact @FactCheck
-
Kevin McConway reposted
Hadley Wickham
@hadleywickham
NYE present: you can now read r-pkgs.had.co.nz and adv-r.had.co.nz from your phone! #rstats
-
Kevin McConway reposted
Andrew Ducker
@andrewducker
This is now my favourite pie chart ever.
-
Post not available here, view on X
Kevin McConway
@kjm2
Some further thoughts in comments on @deevybee excellent #hefcemetrics blog at deevybee.blogspot.co.uk/2014/10/some-thoughts-on-use-of-m… (incuding from me) @jameswilsdon
Kevin McConway
@kjm2
V high correlns but correln isn't equality and biggest losers (10s of £m) from allocn using staff nos are Ox & Cam @deevybee @jameswilsdon
-
Kevin McConway reposted
David Colquhoun on Bluesky 🇺🇦 💙
@david_colquhoun
Very interesting post from @deevybee on metrics deevybee.blogspot.co.uk/2014/10/some-thoughts-on-use-of-m… @jameswilsdon
-
Kevin McConway reposted
Simply Statistics
@simplystats
Data science can't be point and click simplystatistics.org?p=3338
-
Kevin McConway reposted
BPS Research Digest
@ResearchDigest
Most people massively underestimate the pay gap between CEOs and average workers. www.bps.org.uk/2014/09/most-people-think-ceos-are-paid-to…
-
Kevin McConway reposted
David Colquhoun on Bluesky 🇺🇦 💙
@david_colquhoun
Calculation of P values is a form of OCD edge.org/response-detail/25462 by Gerd Gigerenzer” via @trished
-
Kevin McConway reposted
Georgina Mace
@GMMace
Worrying! Ecologists are testing more and more hypotheses, but are their studies are explaining less of the world? news.sciencemag.org/biology/2014/08/ecology-explaining-le…
-
Kevin McConway
@kjm2
Metformin and people without diabetes - I don't think the study says what the press reported. www.sciencemediacentre.org/expert-reaction-to-study-looki…
-
Kevin McConway
@kjm2
I will, but too late tonight!
-
Kevin McConway reposted
Tony Hirst
@psychemedia
Wondering what stories can be told around Dr Foster, #opendata, fearmongering and NHS privatisiation?
-
Kevin McConway reposted
Hetan Shah
@HetanShah
Jeremy Hunt warned over hospital waiting times data www.bbc.co.uk/news/health-28547592
-
Post not available here, view on X
Kevin McConway
@kjm2
I think Jason missed point - shld read G's book as well RT @jasonacollins Evolving Economics: Gigerenzer versus nudge jasonallancollins.wordpress.com?p=20048
-
Kevin McConway reposted
SITPBedford
@SITPBedford
Tomorrow night! New Venue! Great Guest - @martinstaylor ! Cheap Beer! Please RT! #sitp bedford.skepticsinthepub.org/Event.aspx/1973/Hypnotism-wi…
-
Kevin McConway reposted
Olivia Varley-Winter
@ovarwin
Evidence based medicine in crisis? Responses to @bmj_latest article interesting. HT @cochranecollab www.bmj.com/content/348/bmj.g3725?tab=responses
-
Kevin McConway reposted
Michael Grayer
@michaelgrayer
before we get all hysterical abt #tamiflu, read this from @smc_london www.sciencemediacentre.org/expert-reaction-to-cochrane-re… & this from @dianthusmed dianthus.co.uk/tamiflu-its-a-bit-more-complicated-than-that
-
Post not available here, view on X
Kevin McConway
@kjm2
.@trished #tamiflu #cochranereview Review couldn't have been done without access to trial data, sure, but should not be /about/ data access.
Kevin McConway
@kjm2
.@trished #tamiflu #cochranereview Obviously they have to report on data aspects in the Cochrane review, but did they get the balance right?
-
Kevin McConway
@kjm2
.@psychemedia asked for refs on the effect of putting numbers in news. I don't have any. Huge book about the bckgrd:press.uchicago.edu/ucp/books/book/chicago/H/bo3614698.html
-
Kevin McConway
@kjm2
We are back in the station so shouldn't be too long. Don't know how long phone will last.
-
Kevin McConway
@kjm2
Thanks @HetanShah @RoyalStatSoc for tweeting J Humphrys test: I shld also credit @undunc who co-wrote orig article, and Hilly E for the joke
-
Kevin McConway
@kjm2
In Manchester at a conference on causal inference (don't ask). But I do like being in a proper city.
-
Kevin McConway
@kjm2
Me on Statistics in the Media, @WycombeSITP , tomorrow 8pm, Bootlegger, High Wycombe, www.meetup.com/high-wycombe-skeptics/events/103339452/
-
Post not available here, view on X
Kevin McConway
@kjm2
@WycombeSITP Hi, yes got it, have been away /busy, will reply properly later or tomorrow
-
Kevin McConway reposted
SITPBedford
@SITPBedford
Thanks to all the almost 40 who turned up tonight & our great speaker @kjm2 - blog will be updated in the next few days - next event 21/02!
-
Kevin McConway
@kjm2
Me on statistics in the media. Tonight, 7.30, Square pub, #leicester #sitp
-
Kevin McConway
@kjm2
Better go home, I think, before any more funnies strike me.
-
Kevin McConway
@kjm2
I do have fun, don't I?
-
Kevin McConway
@kjm2
Writing teaching text on data summaries and indices. Told to put in more funnies. Added McCullagh on Tukey and prunes rsbm.royalsocietypublishing.org/content/49/537.abstract
-
Kevin McConway
@kjm2
Me on statistics in the media, at Milton Keynes Skeptics in the pub, @MKSkeptics Tomorrow 8pm, Galleon, Old Wolverton, www.mkskeptics.org.uk
-
Kevin McConway
@kjm2
Anyone crazy enough to want to see me putting the world of statistics to rights for an hour should visit bit.ly/MwOtzV forthwith.
-
Kevin McConway
@kjm2
I guess we've got the tobacco industry to thank for all this jubilee stuff. Otherwise her father would've lasted longer & she'd not be at 60
-
Kevin McConway
@kjm2
Reading @mgtmccartney 's book www.pinterandmartin.com/product/The_Patient_Paradox%3A_Wh… . You should too. You need to understand this stuff. Really.
-
Post not available here, view on X
Kevin McConway
@kjm2
@JanMultmeier ach so! Sieht echt aus.
-
Post not available here, view on X
Kevin McConway
@kjm2
@JanMultmeier Echt? Man vermutet spam, phish aber manchmal gibt es Glück.
-
Post not available here, view on X
Kevin McConway
@kjm2
.@James_Fleet @TimHarford I looked at the original message and think it didn't mean 1-6 in that order, but in any order...
Kevin McConway
@kjm2
.@James_Fleet @TimHarford ...anyway husband still wrong because he said 1-6 was more likely, not less.
-
Post not available here, view on X
Kevin McConway
@kjm2
.@mikelcu @TimHarford Indeed, and orig q from wife ambiguous, but husband still wrong. 44 sets of sequential, nearly 14 million others...
Kevin McConway
@kjm2
.@mikelcu @TimHarford ... so if you interpret like that, sequential is less likely but husband said it was more likely.
-
Kevin McConway
@kjm2
... und frohe Weihnachten aus Berlin an alle.
-
Kevin McConway
@kjm2
Hmm. Culture clash. Christmas dinner 16.30 on Christmas Eve, cheese fondue. Nom nom.
-
Kevin McConway
@kjm2
BBC headline wrong shock horror - more blogging from me on cancer screening on the @undunc blog, at understandinguncertainty.org/bbc-website-headline-wrong-s…
-
Kevin McConway
@kjm2
Are British women really top of the European obesity league? Possibly, but just possibly not. By me on @undunc blog at understandinguncertainty.org/are-brits-really-fatter-othe…
-
Kevin McConway
@kjm2
Teaching science by bad example: TED Q&A with @bengoldacre tedconfblog.wordpress.com?p=52279 /via @wordpressdotcom
-
Kevin McConway
@kjm2
More by me, from Berlin, on the @undunc blog at bit.ly/o7CUXQ. German media get rates wrong too.
-
Kevin McConway
@kjm2
Survived first two days at Max Plank Institute for Human Development. In fact, it's been excellent. Hope things continue like this.
-
Kevin McConway
@kjm2
More by me on the @undunc blog at bit.ly/r8GBM8. Cancer, cats, parasites. Hat tip to @edyong209 for blog at blogs.discovermagazine.com/notrocketscience/2011/07/26/is…
-
Kevin McConway
@kjm2
Mobile phones and brain tumours: where did the story go? More from me on the @undunc blog, at bit.ly/opjYCp.
-
Post not available here, view on X
Kevin McConway
@kjm2
.@MarcusduSautoy @rachel787878 Hmm, results don't fit the theory very well. That's life, I suppose.
-
Kevin McConway
@kjm2
You lose one Paul the Octopus, and eight pop up in his place. Blogging from me on @undunc at bit.ly/lyi65K
-
Kevin McConway
@kjm2
More blogging from me on @undunc, on mobile phones again (but a different point). bit.ly/li6aUH
-
Kevin McConway
@kjm2
New entry from me on the @undunc blog at bit.ly/jFFpPA. Mobile phones and cancers.
-
Kevin McConway
@kjm2
Twitter seems to have decided that I, or all the people I follow, or both, are non-persons.
-
Kevin McConway
@kjm2
Bizarre Bayesian joke at bit.ly/lGHosi, but it's also in a proper journal at bit.ly/iONKMt (paywall)
-
Kevin McConway
@kjm2
More @undunc blogging from me, on coffee and cancer bit.ly/jTnrhl and on my uncanny predictive ability bit.ly/mEzSFh
-
Kevin McConway
@kjm2
More @undunc blogging from me, bit.ly/kn2NME, telling you to read @edyong209 at bit.ly/k0ay3C on coffee and breast cancer.
-
Kevin McConway
@kjm2
New blog entry by me on @undunc website, on uncertainty in CVD screening, bit.ly/lHg4ak (Tell me if it makes no sense.)
-
Kevin McConway reposted
Simon Perry
@Simon_Perry
Do cellphones cause brain cancer? bit.ly/fBzUTE probably the most sensible article I've ever read on the subject. NY Times.
-
Kevin McConway
@kjm2
New article on statistical significance, ESP etc. on the @undunc site, bit.ly/fA2u33. Some related links at bit.ly/fxV66g
-
Kevin McConway
@kjm2
In London for mtg at Bank of England. When you get over f-off-human-you're-too-puny buildings, City is interesting.
-
Kevin McConway reposted
Mindy McAdams (not a Dr.)
@macloo
10 useful resources about data visualization: mindymcadams.com/tojou/2011/10-useful-resources-about-dat… (repeat for those who took the weekend off)
-
Kevin McConway
@kjm2
Plenty on disease screening in the news lately. Blog entry by me at bit.ly/dNYR9Y.
-
Kevin McConway
@kjm2
Just did live interview on Radio Wiltshire about child poverty measures. Think I didn't say too much rubbish but you never know with live.
-
Kevin McConway reposted
Information is Beautiful
@infobeautiful
German Green Party MP Malte Spitz sued Deutsche Telekom to release 6 months of mobile phone records. A scar… (cont) deck.ly/~o66Eg
-
Kevin McConway
@kjm2
Anybody fancy sponsoring my daughter's first marathon? bit.ly/dZin1y Excellent good cause (WaterAid).
-
Kevin McConway
@kjm2
Another two new @undunc blog entries from me, on swine flu in Australia bit.ly/gI8evm and schoolbooks in Spain bit.ly/dRdhFV.
-
Kevin McConway
@kjm2
Conf on Visualisation and Presentation in Statistics, Open U, 18 May. bit.ly/fQMEyh Spkrs @undunc @psychemedia and many more. Pls RT
-
Kevin McConway
@kjm2
Two new @undunc blog entries from me, on Google's new magazine bit.ly/hCAJSQ and Tetlock forecasting project bit.ly/gWKIEy.
-
Kevin McConway
@kjm2
What does the Cochrane Review say about presentation of risks? bit.ly/euqnxL
-
Kevin McConway
@kjm2
New phone book delivered. 28% fewer columns of domestic numbers than last year. (Columns same length and typeface.) Must mean something...?
-
Kevin McConway
@kjm2
#ppu @drangiehobbs is Senior Fellow in Public Understanding of Philosophy, (near miss?). Nobody in Economics? Homoeopathy perhaps? (Joke...)
-
Kevin McConway
@kjm2
Profs of Public Understdg: @unduncRisk) @MarcusduSautoy (Science) @RichardWiseman (Psychology), Hal Sosabowski (Sci, Brighton). Others? #ppu
-
Kevin McConway
@kjm2
Top Tips for Dealing with the Press (aka pistols at dawn?) blogs.nature.com/boboh/2011/02/15/manchester-flyer-0311pd… via @AddThis
-
Kevin McConway reposted
David Spiegelhalter
@d_spiegel
Data: can we cope? Blog by Kevin McConway on the articles in Science on data deluge, but which ignore uncertainty understandinguncertainty.org/node/1259
-
Post not available here, view on X
Kevin McConway
@kjm2
@magnusramage markets, dear boy, markets...
-
Kevin McConway
@kjm2
Daryl Bem (with Utts and Johnson) posts a draft response to statistical criticism of his ESP paper, bit.ly/gPETLs. #bem #esp
-
Kevin McConway
@kjm2
Why can't I speak any Arabic? I mean, not a single word. At least I can say Yes and No in Russian, and Hello (or near offer) in Cantonese.
-
Post not available here, view on X
Kevin McConway
@kjm2
@lecanardnoir What has he (Hague) done this time?
-
Kevin McConway
@kjm2
RT from The Register: 'Tree Octopus' proves journos no smarter than 13-year-old Americans reg.cx/1MFm. V. perceptive, I thought
-
Kevin McConway
@kjm2
Lot of blogging about crime maps. My go is at bit.ly/f3jwnj. (I didn't point out that the data are in the Amazon cloud.) #crimemaps
-
Kevin McConway
@kjm2
Slides for apparently excellent talk by Andrew Gelman on infoviz and stat graphics at bit.ly/fsK8zM. And see bit.ly/gLyBj3.
-
Kevin McConway
@kjm2
In Paris. Cold.
-
Kevin McConway
@kjm2
So Coulson resigned because he can't give 110%. 110% of what? Maybe his numeracy wasn't up to it either, or maybe everyone should resign.
-
Kevin McConway
@kjm2
I'll never keep up. RT @undunc:here's a fine list - "40 Fascinating Blogs for the Ultimate Statistics Geek" www.onlinemba.com/resources/
-
Kevin McConway reposted
Ben Goldacre
@bengoldacre
sigh. #bluemonday is trending. but #bluemonday is PR bullshit. humour me, RT and flood the tag. bengoldacre.posterous.com/blue-monday-is-bullshit-churnal…
-
Kevin McConway reposted
David Spiegelhalter
@d_spiegel
great infographic in Guardian www.theguardian.com/news/datablog/2011/jan/14/mortality-s… - see also www.nhs.uk/Tools/Pages/NHSAtlasofrisk.aspx for an animated version of causes of death
-
Kevin McConway
@kjm2
Drain fixed. (Not by me.)
-
Kevin McConway
@kjm2
Resolution: say more on Twitter. Why? Because it is there.
-
Kevin McConway
@kjm2
So, the last time I was in Hereford was 49 years ago, and it looks like nothing has changed. Excellent.
-
Kevin McConway
@kjm2
Hmm, Hereford tomorrow, not sure whether I can take the ritual upon ritual.
-
Kevin McConway
@kjm2
gotto gotobed so that can gotowork tomorrow aaagghh
-
Kevin McConway
@kjm2
got up too early. Again.
-
Kevin McConway
@kjm2
doesn't get Tradition
-
Kevin McConway
@kjm2
not sleeping
-
Kevin McConway
@kjm2
trying to make sense of what the QAA is for (and failing)
-
Kevin McConway
@kjm2
wondering
-
Kevin McConway
@kjm2
Trying, yet again, to make sense of Twitter
-
Kevin McConway
@kjm2
Wondering why I bother reading all that garbage in blogs. Do there exist good ones?


































































