Latest updates for Dubious Statistics
Fresh curated links around Dubious statistics are collected here so marketers can spot useful updates and turn timely ideas into posts faster.
Recent items include:
- Misrepresentative metrics
- Recent discoveries on the acquisition of the highest levels of statistical fallacies
- Dirty comparisons
Post angles to try
Fresh articles and ideas
Recent curated links from global sources. Generate one free draft from any story, then use SocialBu to schedule and refine your content calendar.
Recent discoveries on the acquisition of the highest levels of statistical fallacies
Mark Goldstein points us to this post by Alex Dimakis, who writes: A paper was recently published in Science on highest level of human performance across athletics, science, math a...
Dirty comparisons
RNZ: NZ among world’s worst for landfill waste per person RNZ: New Zealand generates double the global average of rubbish, report says (also repeated here and here) This attribute...
Voters contend with ‘dodgy’ data in party leaflets for English local elections
Exclusive: Investigation into campaigning materials for local polls in May challenges tactical voting claims Election leaflets are providing “grotesque” information about how to vo...
Figures Don’t Lie But...
DesistersIf you listen to Republicans or conservative you would think that it is around 80 or 90 percent of the trans children detransition. That lie goes back to studies in Nether...
The problem with healthy life expectancy
A crude blend of very different statistics is not the best tool for the job
Survey Statistics: dCV for MRP ?
Three weeks ago we learned about design-based cross validation (dCV), shown in Figure 1(d) of Iparragirre et al. (2023): Each dot is a PSU (primary sampling unit), which can be an...
A false high: On voter turnout data, SIR impact
SIR’s impact must be factored in before reading turnout figures
Is More Always More?: Why Church Statistics Don’t Always Reflect Success
by Reinder Bruinsma | 1 May 2026 | It was the time of the judges, around 1200 BCE. Israel did not yet have a king, so when they were troubled by their neighbors, a temporary rul...
Survey Statistics: double-plus robustness
Meng (2022) pops up a lot here: “it is the people” (the launch of this blog series a year ago !), “probability samples vs epsem samples vs SRS samples”, “divine probabilities”, and...
Bloody Statistics..And Alemtuzumab
I have been taken to task out my slipshod use of statistics and suggested about 50% get disease control after two doses and about 50% after three doses so that with three doses abo...
Why Superior Scientists, will never rely on Non-Inferiority trials?
Statistics is the most advanced form of mathematics by which predictions about the future can be made with some degree of surety It is the vital cog linking biology and maths. Howe...
Here’s a story from Australia: There were so many problems with the survey that the government didn’t release the data.
From the Australian Bureau of Statistics: On 17 July 2025 the Australian Bureau of Statistics (ABS) announced that it will not release statistics from the 2023-24 Survey of Income...
Half of AI Health Answers Are Wrong Even Though They Sound Convincing – New Study
AI appears to perform no better than astrology, yet even the author of this critical piece defends its use in medicine.
Putin’s Misleading Factoids on Russia-Israel Ties
Many, perhaps in part due to Putin-myth-stoking, think more Israelis are close to Russia than is demonstrably the case.
Why metrics sometimes hide the real problem
Numbers create a particular kind of confidence. When an organisation can point to measurable evidence of performance — targets met, growth achieved, efficiency improved — there is....
Oh crikey Trump
This is quite a scary statistic in difficult times.
Survey Statistics: irrelevant alternatives ?
Choice models are useful for modeling elections (or RuPaul’s Drag Race). Consider vote choice with candidates C = {Left, Right, Other}. “Other” can be a third party, not voting, or...
Vague Patch Notes: The bad data problem with MMOs
Do you want to know how many monthly active players Guild Wars 2 has? If so, I’ve got a math exercise for you. (If not, pretend you do for the moment.) First, look up the most rece...
Faith: Understanding statistics after the withdrawal of ‘quiet revival’ claims
FOR a brief period, recently, the phrase “quiet revival” entered public conversation with a certain tentative confidence. A report suggested that church attendance in Britain was r...
Chart claiming to show immigrants' 'illegal entries' to US under Biden misrepresents real data
Sure, numbers don't lie. But statisticians can present data in ways to fit chosen narratives.
NZTA much better?
This is an expansion from the “Briefly” post about an NZTA summary of public comment on their SH1 Wellington proposals. On Bluesky, @gwynebs had pointed out that some of the bars i...
‘Staggering’ number of people believe unproven claims about vaccines, raw milk and more
Survey results suggest a rise in questioning of scientific evidence
Do we really know how many people are listening to the radio? A deep dive into the science of the JNLRs
“I don’t believe in the JNLRs. I never have,” the broadcaster Pat Kenny told the Sunday Independent recently. “I think it’s not a very scientific way of measuring audiences.”
Turn fresh research into a full content calendar
Use SocialBu to discover ideas, generate post drafts, and schedule them across your social channels.