March 14, 2025

Denominators

Earlier this week, Wikipedia’s front-page “Did you know…” section this week referenced the year that Vatican City had the world’s highest murder rate. In 1998, a double homicide in the Swiss Guards put the murder rate over 200 per 100,000 inhabitants, more than twice the rate in any of the Caribbean countries that usually head the list and roughly infinity times the usual rate in recent years when it has been a separate country. That’s a real rate, with the right denominator, it’s just that the year to year variability makes rates a relatively unhelpful summary.

Vatican City has a denominator problem for minor crimes; in 1992 there were 392 ‘civil offences’ and 608 ‘penal offences’, working out to a bit less than 100% and a bit more than 100% of the number in resident population.  The problem is that the tiny state has many millions of  visitors per year and they, rather than the resident population, are both the perpetrators and victims of the minor crimes.  The resident population isn’t the right denominator.

A less dramatic version of this problem showed up when looking at rates of violent crime in parts of central Wellington some years back.

March 12, 2025

More Panadol scare headlines

The New York Post is saying

Attention-deficit/hyperactivity disorder is a common behavioral condition that affects approximately 7 million US children, including about a million kids diagnosed since 2016.

The reason for the recent rise in diagnoses is under debate — a new study in the journal Nature Mental Health suggests the culprit could be in your medicine cabinet.

They’re talking about paracetamol (or as Americans call it, acetaminophen).  There’s a new study that looks at a fairly small group of US mothers and kids and finds weak evidence of a correlation between ADHD diagnosis in the kid and use of paracetamol by the mother.   You might remember this topic from previous StatsChat episodes.  There was  originally a Danish study that was surprised to stumble across a correlation. A New Zealand study checking up on the correlation also found it.

A Spanish study resulted in the NZ Herald (from the Daily Mail) scare headline One paracetamol in pregnancy could raise risk of autism. This was especially egregious since not only did the study say nothing about ‘one paracetamol’ and wasn’t really about autism, it actually found lower rates of the symptoms in kids whose mothers took paracetamol. The study argued that while the rates were lower in those kids, they should have been even lower based on other risk factors.   At this point it was all plausible and maybe a bit concerning but not reason for major change in medical practice — after all, mothers aren’t taking Panadol for fun.

In 2023, a combination of most of the published studies estimated a slight increase in risk, about 25%.  On the other hand, A very big Swedish study, using data from everyone born in Sweden from 1995 to 2019, then found no suggestion of a correlation.

So what’s the point of this new study? Well, one of the issues in interpreting these correlation studies is that many of them didn’t know for sure who actually took paracetamol.  For normal people this would be a big issue — lots of medications include paracetamol, and you might easily miss some, or just forget. Pregnant women, though, tend not to just casually take cough syrup or whatever.  Even so, if you happened to have data lying around from blood samples which told you who had taken paracetamol, you might be interested in seeing what the correlation was like.   So they did. And the correlation was broadly similar to what the small, early studies had seen: kids whose mothers blood samples showed paracetamol were about twice as likely to have ADHD.  That’s nice to know, even if it’s not a big change in the evidence.

We still have the conflict between ‘no sign of a correlation’ in the big Swedish study and ‘about 25% higher’ in the combined smaller studies.  It’s possible that paracetamol has an effect and that the Swedish study missed it because it didn’t measure paracetamol use as accurately. It’s also possible that the reasons for taking paracetamol (eg illness, fever) are what causes ADHD. Or it could all be some sort of bias and the Swedish study could be correct. It’s hard to tell.  Ask your doctor, etc.

The new study, of course, does not suggest paracetamol is responsible for recent trends in ADHD diagnosis: that claim is down to the New York Post, and is pretty clearly wrong. Here’s the trend:

Paracetamol became popular as a relatively safe, over-the-counter treatment a long time ago now. It might have been response for an ADHD trend in, say,  the 1980s, but not a trend in the 21st century.

Briefly

  • The New York Times has an interactive with graphs showing how everything changed when Covid started.  It’s also an explanation of why it’s hard to estimate the effects of specific actions on Covid: everything changed at once
  • Visualising how different languages represent animal noises: the spellings can look very different, but the underlying phonetics are more similar
  • “The answer to the how-many-significant-digits problem is the same as the answer to the what-to-graph problem: The click-through solution“. Or in other words, you can have tables without stupid numbers of digits and let people who want detail click to see it
  • The website of the US Centers for Disease Control as it existed on Jan 6 has been copied to RestoredCDC.org, hosted in Europe.  This won’t help with ongoing data collection, but it does make the past data from the CDC more reliably available.
March 11, 2025

United Rugby Championship Predictions for Week 13

Team Ratings for Week 13

The basic method is described on my Department home page.
Here are the team ratings prior to this week’s games, along with the ratings at the start of the season.

Current Rating Rating at Season Start Difference
Leinster 13.75 12.09 1.70
Glasgow 8.10 9.39 -1.30
Bulls 7.44 8.83 -1.40
Munster 4.39 9.28 -4.90
Lions 4.35 6.73 -2.40
Stormers 4.23 6.75 -2.50
Sharks 1.78 -2.94 4.70
Edinburgh 1.54 0.09 1.50
Cheetahs 0.80 0.80 0.00
Ospreys -0.01 -2.51 2.50
Ulster -0.55 2.52 -3.10
Connacht -1.62 -0.76 -0.90
Scarlets -3.42 -10.65 7.20
Benetton -3.62 1.02 -4.60
Cardiff Rugby -5.70 -2.55 -3.10
Southern Kings -6.52 -6.52 0.00
Zebre -9.65 -16.17 6.50
Dragons -15.29 -15.41 0.10

 

Performance So Far

So far there have been 96 matches played, 69 of which were correctly predicted, a success rate of 71.9%.
Here are the predictions for last week’s games.

Game Date Score Prediction Correct
1 Sharks vs. Lions Mar 09 25 – 22 -0.90 FALSE

 

Predictions for Week 13

Here are the predictions for Week 13. The prediction is my estimated expected points difference with a positive margin being a win to the home team, and a negative margin a win to the away team.

Game Date Winner Prediction
1 Cardiff Rugby vs. Lions Mar 22 Lions -4.60
2 Glasgow vs. Munster Mar 22 Glasgow 9.20
3 Sharks vs. Zebre Mar 22 Sharks 16.90
4 Benetton vs. Edinburgh Mar 23 Benetton 0.30
5 Bulls vs. Leinster Mar 23 Leinster -0.80
6 Dragons vs. Ulster Mar 23 Ulster -9.20
7 Ospreys vs. Connacht Mar 23 Ospreys 7.10
8 Scarlets vs. Stormers Mar 23 Stormers -2.20

 

Super Rugby Predictions for Week 5

Team Ratings for Week 5

The basic method is described on my Department home page.
Here are the team ratings prior to this week’s games, along with the ratings at the start of the season.

Current Rating Rating at Season Start Difference
Blues 13.11 14.92 -1.80
Chiefs 12.32 11.43 0.90
Crusaders 9.25 8.99 0.30
Hurricanes 8.59 10.97 -2.40
Brumbies 5.34 6.19 -0.90
Reds 1.06 1.35 -0.30
Highlanders -1.95 -2.50 0.60
Waratahs -4.44 -5.17 0.70
Fijian Drua -6.03 -7.98 1.90
Western Force -6.78 -6.41 -0.40
Moana Pasifika -9.93 -11.25 1.30

 

Performance So Far

So far there have been 20 matches played, 14 of which were correctly predicted, a success rate of 70%.
Here are the predictions for last week’s games.

Game Date Score Prediction Correct
1 Blues vs. Brumbies Mar 07 20 – 21 12.90 FALSE
2 Fijian Drua vs. Chiefs Mar 08 28 – 24 -15.90 FALSE
3 Moana Pasifika vs. Hurricanes Mar 08 40 – 31 -16.90 FALSE
4 Waratahs vs. Western Force Mar 08 34 – 10 4.30 TRUE
5 Crusaders vs. Reds Mar 09 43 – 19 11.10 TRUE

 

Predictions for Week 5

Here are the predictions for Week 5. The prediction is my estimated expected points difference with a positive margin being a win to the home team, and a negative margin a win to the away team.

Game Date Winner Prediction
1 Highlanders vs. Hurricanes Mar 14 Hurricanes -7.00
2 Brumbies vs. Fijian Drua Mar 14 Brumbies 14.90
3 Crusaders vs. Western Force Mar 15 Crusaders 20.00
4 Chiefs vs. Blues Mar 15 Chiefs 2.70
5 Reds vs. Waratahs Mar 15 Reds 9.00

 

NRL Predictions for Round 2

Team Ratings for Round 2

Unfortunately my predictions for the first round were incorrect because I had the Dolphins playing at home, when in fact the Rabbitohs were at home. The results below use the correct home ground and show the Rabbitohs as predicted winners rather than the Dolphins.

The basic method is described on my Department home page.
Here are the team ratings prior to this week’s games, along with the ratings at the start of the season.

Current Rating Rating at Season Start Difference
Storm 10.26 9.29 1.00
Panthers 8.71 8.50 0.20
Roosters 5.66 7.44 -1.80
Sharks 4.89 5.10 -0.20
Sea Eagles 4.13 2.97 1.20
Cowboys 2.96 4.11 -1.20
Bulldogs 0.43 0.07 0.40
Broncos -0.04 -1.82 1.80
Knights -0.38 -0.05 -0.30
Dolphins -2.07 -1.96 -0.10
Raiders -2.59 -3.61 1.00
Warriors -2.69 -1.68 -1.00
Eels -3.99 -3.02 -1.00
Rabbitohs -4.23 -4.35 0.10
Dragons -4.90 -4.55 -0.30
Titans -5.50 -5.50 -0.00
Wests Tigers -10.64 -10.97 0.30

 

Performance So Far

So far there have been 8 matches played, 6 of which were correctly predicted, a success rate of 75%.
Here are the predictions for last week’s games.

Game Date Score Prediction Correct
1 Raiders vs. Warriors Mar 02 30 – 8 -1.90 FALSE
2 Panthers vs. Sharks Mar 02 28 – 22 3.40 TRUE
3 Roosters vs. Broncos Mar 06 14 – 50 12.30 FALSE
4 Wests Tigers vs. Knights Mar 07 8 – 10 -7.90 TRUE
5 Rabbitohs vs. Dolphins Mar 07 16 – 14 0.60 TRUE
6 Dragons vs. Bulldogs Mar 08 20 – 28 -1.60 TRUE
7 Sea Eagles vs. Cowboys Mar 08 42 – 12 1.90 TRUE
8 Storm vs. Eels Mar 09 56 – 18 15.30 TRUE

 

Predictions for Round 2

Here are the predictions for Round 2. The prediction is my estimated expected points difference with a positive margin being a win to the home team, and a negative margin a win to the away team.

Game Date Winner Prediction
1 Knights vs. Dolphins Mar 13 Knights 4.70
2 Warriors vs. Sea Eagles Mar 14 Sea Eagles -3.30
3 Panthers vs. Roosters Mar 14 Panthers 6.00
4 Dragons vs. Rabbitohs Mar 15 Dragons 2.30
5 Cowboys vs. Sharks Mar 15 Cowboys 1.10
6 Raiders vs. Broncos Mar 15 Raiders 0.40
7 Eels vs. Wests Tigers Mar 16 Eels 9.60
8 Bulldogs vs. Titans Mar 16 Bulldogs 8.90

 

AFL Predictions for Week 2

Team Ratings for Week 2

The basic method is described on my Department home page.
Here are the team ratings prior to this week’s games, along with the ratings at the start of the season.

Current Rating Rating at Season Start Difference
Hawthorn Hawks 23.59 21.95 1.60
Brisbane Lions 22.65 22.65 -0.00
Western Bulldogs 18.20 18.20 0.00
Geelong Cats 15.04 15.04 0.00
GWS Giants 11.68 9.08 2.60
Sydney Swans 10.97 12.60 -1.60
Port Adelaide Power 7.63 7.63 -0.00
Fremantle Dockers 5.99 5.99 0.00
Carlton Blues 5.01 5.01 -0.00
Collingwood 2.78 5.39 -2.60
Adelaide Crows 2.69 2.69 -0.00
St Kilda Saints 0.89 0.89 0.00
Melbourne Demons -0.21 -0.21 -0.00
Gold Coast Suns -6.41 -6.41 0.00
Essendon Bombers -10.15 -10.15 -0.00
Richmond Tigers -31.00 -31.00 0.00
West Coast Eagles -34.67 -34.67 -0.00
North Melbourne -37.08 -37.08 0.00

 

Performance So Far

So far there have been 2 matches played, 1 of which were correctly predicted, a success rate of 50%.
Here are the predictions for last week’s games.

Game Date Score Prediction Correct
1 Sydney Swans vs. Hawthorn Hawks Mar 07 76 – 96 1.60 FALSE
2 GWS Giants vs. Collingwood Mar 09 104 – 52 14.70 TRUE

 

Predictions for Week 2

Here are the predictions for Week 2. The prediction is my estimated expected points difference with a positive margin being a win to the home team, and a negative margin a win to the away team.

Game Date Winner Prediction
1 Richmond Tigers vs. Carlton Blues Mar 13 Carlton Blues -36.00
2 Hawthorn Hawks vs. Essendon Bombers Mar 14 Hawthorn Hawks 33.70
3 Geelong Cats vs. Fremantle Dockers Mar 15 Geelong Cats 20.00
4 Sydney Swans vs. Brisbane Lions Mar 15 Brisbane Lions -0.70
5 Collingwood vs. Port Adelaide Power Mar 15 Collingwood 6.20
6 Western Bulldogs vs. North Melbourne Mar 15 Western Bulldogs 55.30
7 Adelaide Crows vs. St Kilda Saints Mar 16 Adelaide Crows 12.80
8 Melbourne Demons vs. GWS Giants Mar 16 GWS Giants -0.90
9 West Coast Eagles vs. Gold Coast Suns Mar 16 Gold Coast Suns -17.30

 

March 7, 2025

Painkillers and dementia

Q: Did you see that ibuprofen prevents dementia?

A: No

Q: Common 3p anti-inflammatory pill ‘can help prevent dementia’ says new study And Prolonged Use Of Anti-Inflammatory Pills May Help Prevent Dementia: StudyAnd…

A: No

Q: Those quotes in the first headline imply someone really said it

A: Well, that used to be the convention, but apparently not in this case.

Q: Mice?

A: No, not mice. People

Q: Correlations, or randomised trials?

A: Correlations

Q: Is there a paper?

A:  There is a paper.

Q: Has anyone looked at this correlation before?

A: Oh my yes. So many people. There are even randomised trials. The Cochrane Review says “no evidence that it works, and it may be dangerous”

Q: What do the scientists say about that?

A: The trials were too short to show the effect, or they started too late in the disease process.

Q: Is that possible?

A: Sure, it’s possible. Lots of things are possible.

Q: So you don’t believe the paper?

A: It’s a perfectly reasonable paper for consenting scientists in private (I know some of the authors), but it doesn’t justify the recommendation of long-term treatment with these drugs for the prevention of dementia, especially given the potential adverse effects

Q: Well, that’s your opinion. What do the scientists who wrote the paper say?

A: Our results.. do not justify the recommendation of long-term treatment with NSAIDs for the prevention of dementia, given its potential adverse effects. 

Age distributions

A question from a reader, based on  this NZ Herald article
“Bowel cancer does not discriminate on race. Māori and Pacific peoples have a similar risk of developing bowel cancer compared to other population groups at a given age.
“It was true that a higher proportion of bowel cancers occur in Māori and Pacific peoples at a younger age, but that is because the overall demographics of those groups are younger. It has always been age that determines bowel cancer risk, not race”

I thought that this required more explanation. Proportion at an age does not seem to me to depend on the demographics of those ages

It’s a good question.  The minister is plausibly correct that the younger age at diagnosis for Māori and Pacific Peoples is driven substantially by demographics.   That is, one reason that few very elderly Māori get diagnosed with bowel cancer is that there aren’t many very elderly Māori.  Fewer Māori make it to be very elderly, and also the Māori population is increasing both because of higher birth rate and because more people are now identifying as Māori to the healthcare system.   If you have the same age-specific incidence rates in two groups, but one group averages younger, the incidence in the younger group will tend to be at younger ages.

That’s not the whole story, or even most of it, for this decision.  The age distribution being quoted is age at diagnosis (because that’s what you have for cancer), but diagnosis isn’t equally distributed. According to the HQSC atlas of health care variation, Māori are more likely to be diagnosed with bowel cancer following emergency presentation, and more likely to die within two years of diagnosis. This means there’s a good case that Māori are more underdiagnosed than New Zealand Europeans.   On the other hand, a lot of the problem with underdiagnosis is not being tested. If people end up just doing one test when they become eligible, and then not bothering later, the optimal age for a single test is more like 60 than 50.   And, as a general principle,  if you want to spend public money to improve health, you typically will do better by spending it on people who are less healthy and have worse access to health care.

In any case, while the headline Bowel cancer screening eligibility age to be lowered for everyone is technically true (since the lower-age screening pilot has already been stopped), it seems to miss the point a little.

March 4, 2025

United Rugby Championship Predictions for Delayed Games

Team Ratings for Delayed Games

The basic method is described on my Department home page.
Here are the team ratings prior to this week’s games, along with the ratings at the start of the season.

Current Rating Rating at Season Start Difference
Leinster 13.75 12.09 1.70
Glasgow 8.10 9.39 -1.30
Bulls 7.44 8.83 -1.40
Lions 4.79 6.73 -1.90
Munster 4.39 9.28 -4.90
Stormers 4.23 6.75 -2.50
Edinburgh 1.54 0.09 1.50
Sharks 1.35 -2.94 4.30
Cheetahs 0.80 0.80 0.00
Ospreys -0.01 -2.51 2.50
Ulster -0.55 2.52 -3.10
Connacht -1.62 -0.76 -0.90
Scarlets -3.42 -10.65 7.20
Benetton -3.62 1.02 -4.60
Cardiff Rugby -5.70 -2.55 -3.10
Southern Kings -6.52 -6.52 0.00
Zebre -9.65 -16.17 6.50
Dragons -15.29 -15.41 0.10

 

Performance So Far

So far there have been 95 matches played, 69 of which were correctly predicted, a success rate of 72.6%.
Here are the predictions for last week’s games.

Game Date Score Prediction Correct
1 Munster vs. Edinburgh Mar 01 28 – 34 10.80 FALSE
2 Zebre vs. Dragons Mar 01 31 – 21 11.50 TRUE
3 Lions vs. Sharks Mar 02 38 – 14 3.00 TRUE
4 Bulls vs. Stormers Mar 02 16 – 19 7.30 FALSE
5 Leinster vs. Cardiff Rugby Mar 02 42 – 24 26.90 TRUE
6 Ulster vs. Scarlets Mar 02 30 – 28 10.20 TRUE
7 Connacht vs. Benetton Mar 02 38 – 30 7.40 TRUE
8 Glasgow vs. Ospreys Mar 02 31 – 32 16.10 FALSE

 

Predictions for Delayed Games

Here are the predictions for Delayed Games. The prediction is my estimated expected points difference with a positive margin being a win to the home team, and a negative margin a win to the away team.

Game Date Winner Prediction
1 Sharks vs. Lions Mar 09 Lions -0.90