Stats Chat

Stuff has a story on robot-assisted surgeries, claiming

Patients who have robot-assisted surgeries on their kidneys or prostate have shorter hospital stays and a lower risk of having a blood transfusion or dying – but the bill is significantly higher, a study found.

That’s not quite what the study found.  The abstract says

While robotic assisted and laparoscopic surgery are associated with fewer deaths, complications, transfusions and shorter length of hospital stay compared to open surgery, robotic assisted laparoscopic surgery is more costly than laparoscopic and open surgery.

The researchers used the Nationwide Inpatient Sample, a random subset of US hospital admissions, to compare three approaches to prostate and kidney surgery: laparoscopic (‘keyhole’) surgery by hand, robot-assisted laparoscopic surgery, and open (non-keyhole) surgery.  They found that laparoscopic surgery, whether robot-assisted or not, was safer than open surgery, but they didn’t report an advantage of robot over non-robot keyhole surgery, just an increase in cost.

Now, you might well be muttering about causation and correlation, and asking “How do we know the open surgeries weren’t just more difficult cases?” If you aren’t, then you can start now and I’ll let you pretend you were doing it all along.  Since surgeon experience makes a big difference, we should also worry whether it’s the most experienced surgeons who get the expensive and shiny new robots.

The researchers did try to cope with this problem using a technique called propensity scores.  Essentially, they tried to classify patients according to how likely they were to have an open surgery vs manual laparoscopic surgery vs a robot surgery, and match the patients so comparisons were done only between similar cases.  However, the researchers did say in the main body of the paper  “Results from unadjusted and propensity adjusted analyses were largely similar”, ie, the attempt to remove bias didn’t actually remove any bias.  The optimistic view is that this means there wasn’t any bias; the pessimistic realistic view is that it means the adjustment probably failed.

Surgical robots have been a bit of a disappointment.  It’s not that they don’t work, but they were supposed to have huge and dramatic advantages (over and above “ooh, shiny”) and these huge advantages don’t seem to have materialized.

Thank you for all the suggestions for Stats Crimes (feel free to continue to add your thoughts there too).

We thought you might be interested in a little insight into what the Department of Statistics at the University of Auckland came up with as their pet peeve Stats Crimes during their annual staff retreat recently.

Here’s just a few of them, I’ll post more soon:

Random vs ‘random’

Talkback radio and others not understanding that their listeners and viewers (audience) are not a random population, however ‘random’ they may be.

Definitions and changing definitions

Defining the “measure” they are talking about e.g. poverty, quality of life, employment data. Not stating that “measures” have changed – i.e. definition or classification. Often changes in definition or classification is part of the reason for an increase e.g. autism.

Not really that amazing

Coincidences are more likely than you think.

Association vs causation

Causal headlines from observational studies. “People who are poor watch too much TV. Get rid of TV no more poor people!” (Made this up.)

Bad graphs

Pie charts should be outlawed as comparison of size (areas) are impossible – should use barcharts. 3D graphs should also be outlawed. Chart junk. Uninformative graphics.

Thank you for all the fantastic Stat of the Summer nominations.

Two of them generated popular posts on Stats Chat:

• Unfaithful to the data, too – Jennifer Muller’s nomination of Infidelity: it’s a right-wing, meat-eaters’ thing
• Tip of the Icecube – Stephanie Mills’ nomination of Unfit to teach – the roll of shame

The winner was chosen to be Eric Crampton’s nomination of smoker costs from The Quit Group, quoted on Radio NZ for smokers each costing the economy $139,000/year.

If it were true, the sky would fall in.

While the original source provided a form of correction to Eric for the smoking number, as far as we know Radio NZ didn’t correct the report.

Congratulations Eric for winning a copy of Tufte’s book “Beautiful Evidence”.

Thank you to everyone who took part and we are now resuming our weekly competition, so please keep your nominations coming in!

The Herald

More than 25,000 animals including fish have died during research and teaching at the University of Otago since 2009, and the figures are expected to increase significantly when statistics are collated for 2011.

No, really?  Going from a two-year total to a three-year total will result in an increase?

We collect multiple years of data for two main reasons: to compute averages (reducing statistical noise) and to compute differences (to learn about trends). Computing totals across multiple years is rarely helpful.

The Otago Daily Times does a better job: it uses the multiple years of data to give trends

Animal use by different groups in New Zealand has dropped by 29% during a three-year period from a record high of 341,520 recorded in 2008.

and

The number of animals being used for research purposes by universities in 2010 has dropped 43% from a high of 123,739 in 2008.

Each week, we would like to invite readers of Stats Chat to submit nominations for our Stat of the Week competition and be in with the chance to win an iTunes voucher.

Here’s how it works:

• Anyone may add a comment on this post to nominate their Stat of the Week candidate before midday Friday March 9 2012.
• Statistics can be bad, exemplary or fascinating.
• The statistic must be in the NZ media during the period of March 3-9 2012 inclusive.
• Quote the statistic, when and where it was published and tell us why it should be our Stat of the Week.

Next Monday at midday we’ll announce the winner of this week’s Stat of the Week competition, and start a new one.

(more…)

The American Journal of Clinical Nutrition missed an opportunity when they put a meta-analysis of randomized studies of chocolate in the March issue rather than the February issue, but that hasn’t stopped the media coverage.  Stuff has a headline asking “Is chocolate really heart-healthy?”  There’s a law of journalism that states any headline ending in a question mark can be answered by the word “No”, and Stuff does not disappoint us here.

The newspaper story is actually pretty good — very good by the standards of nutrition journalism.  There are four key points, and the story makes three of them clearly and alludes to the fourth (more…)

I will be producing predictions for the NRL this year as well as for the Super 15.

Ratings at the Beginning of the 2012 NRL Season

Here are the team ratings at the start of the NRL season.

Predictions for Round 1

I got caught out with the game starting tonight. I thought I had another day before producing my predictions. Anyway, here are the predictions for Round 1. The prediction is my estimated points difference with a positive margin being a win to the home team, and a negative margin a win to the away team.

Team Ratings for Week 2

Here are the team ratings prior to Week 2, along with the ratings at the start of the season. Interestingly for 3 teams the ratings have not changed. That is because the Rebels had a bye, and for the Stormers versus Hurricanes, I got the margin correct (rounded to 2 decimal places). My predicted margin was also very close for the Brumbies versus Force game.

Performance So Far

So far there have been 7 matches played, 4 of which were correctly predicted, a success rate of 57.1%.

Here are the predictions for the games so far.

Predictions for Week 2

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

During the Christmas news-deficiency season there was a story warning people to be careful around all the dangerous holiday accident risks.  Our Stat of the Week award went  to Sonia Pollak, who pointed out that 3040 accidents predicted for Christmas Day was quite a bit lower than the average for other days.

The story has returned in the past tense.  The ACC is reporting 3238 accident claims for Christmas Day (close to what they predicted, about 25% lower than an average day) and $850,000 in claims.  Even assuming that the initial claims relate only to medical treatment, that’s about half of the average daily expenditure  (medical treatment, $512 million/yr, hospital treatment – $199.3 million/yr)

We could prevent accidents and save money by being especially careful on Christmas Day.  But we could probably prevent more accidents and save more money by being especially careful on some other day, such as the anniversary of some significant historical accident.  I suggest June 14.

There’s still a little more time to add your nominations for the Stat of the Summer competition, and here’s the most recent two nominations from Tony Cooper:

Divided Auckland – NZ Herald series

“it was flawed because they assumed as truth something that is only a hypothesis and assumed that correlation implies causation (that inequality causes poverty”

Read his full nomination »

West Coast/Buller among the happiest regions

“The thing that struck me as odd, almost humorous, about this story which reports that West Coast/Buller is the happiest region in NZ is that in 2008 the survey reported the same region as the LEAST happiest. Surely the region hasn’t changed that much in that little time!

My best guess is that this is an example of getting the sampling error wrong.”

Read his full nomination »