Slashdot Mirror
Science and the Shortcomings of Statistics
Kilrah_il writes "The linked article provides a short summary of the problems scientists have with statistics. As an intern, I see it many times: Doctors do lots of research but don't have a clue when it comes to statistics — and in the social science area, it's even worse. From the article: 'Even when performed correctly, statistical tests are widely misunderstood and frequently misinterpreted. As a result, countless conclusions in the scientific literature are erroneous, and tests of medical dangers or treatments are often contradictory and confusing.'"
How do you figure that? My latest calculations placed it at 70% [Note: Error +/- 10%].
It's not just statistics that people have a problem with...
-- Braden's law of data: All data spends some of its lifetime in an excel spreadsheet.
Our company six sigma training included two weeks of collecting and analyzing data with a stats package. I got enough experience to even train me how to use the program. I can still do a few things that come up regularly. Probably the best thing to come out of six sigma (for me at least).
that there are only 3 kinds of scientists: those that are good at math and those that aren't.
Game: Player 'Donald J Trump' now has AI skill level 'experimental'.
I think your example would be more persuasive if it involved algebra, though.
As with everything, xkcd delivers. My personal favorite :)
People often get caught assuming that Correlation == Causation.
Cheers, Chris
Exactly. I would never believe a statistic that I did not make up myself!
Science advances one funeral at a time- Max Planck
I don't have to be a statistician to know that the above post is 97% bullshit.
Unfortunately, it is hard to break a viscous cycle. The high viscosity makes it easy to get stuck.
"FDA staff reviewers expressed concern about the number of patients who were left out of the study because they died."
Yes, it's rarely mentioned that causation implies correlation.
Interestingly, I have observed a correlation between people who cite that "correlation != causation" and those who ignore "causation implies correlation" in their arguments.
Lars T.
To the guy who modded me down from perfect to terrible Karma - Apple haters still suck
In other news, researches proved that water causes cancer. 100% of the cancer patients that died in 2009 drank water regularly.
Stupidity is an equal opportunity striker.
Fellow slashdotter Bill Dog
*Only for nonzero values of pope.
I read TFA and all I got was this lousy cookie
That particular oversight drives me nuts. An extension of that is when someone uses orthogonal polynomial contrasts and multiple comparison tests on the same data without adjusting their alpha level. If Tukey's HSD accounts for all tests and gives you an overall alpha of 0.05, and you then proceed to run linear and quadratic contrasts, the combined alpha level is actually 0.10, not 0.05 because Tukey's doesn't adjust for contrasts and contrasts don't contain adjustments for multiple comparisons.
I'm actually at a scientific meeting and saw 7 presentations in which they "double dipped" on their statisitics before we broke for lunch.
Bureaucracy expands to meet the needs of the expanding bureaucracy.-Oscar Wilde
Interestingly, I have observed a correlation between people who cite that "correlation != causation" and those who ignore "causation implies correlation" in their arguments.
Ah yes, but can you suggest any causal relationship between those two observations?
Better to be despised for too anxious apprehensions, than ruined by too confident a security. --Edmund Burke
Not only that, but it is also the key ingredient in most of today's problems. It's the core element of acid rain, it's a main ingredient in beer and many other alcoholic beverages that cause families to break apart, you find it in fattening food and it is the main ingredient in all high carbon soft drinks.
Consuming that stuff might also lead to antisocial behaviour, as it has been confirmed that all murderers, gunmen and even terrorists have consumed it pretty much all their life. When are we going to ban that substance? Doesn't anyone think of the children anymore?
Please read on. It is a serious problem and people should be informed urgently. Giving one sided, biased and doctored results is a really urgent problem in today's statistics and presentation of information. I beg you, make sure you read it and heed the warning. Think of the children!
We used to have a Bill of Rights. Now, with the rights gone, all we have left is the bill.
*Ahem* Cue carbon dating.
To be fair the problem with carbon dating is not merely curve fitting. A larger problem is the when God created the universe in Oct 4004BC (or thereabouts), He created Adam with a belly-button.
Better to be despised for too anxious apprehensions, than ruined by too confident a security. --Edmund Burke
I feel somewhat vindicated for being no good at econometrics when I see where the people who were good at it have landed us.....
Physics (yes, Physics, THE hardest of hard sciences) is full of terrible mathematics, absolutely terrible, shockingly bad stuff. The good ones know it, some will say it doesn't matter because their butchery comes up with "accurate" results. If they can't even get their analysis right, what can we expect of the softer sciences? That said physics is not so much concerned with statistics as it is probability, none the less, they have some serious problems, for example they often simply decide highly non-convergent things should converge because the experiment says it should...
The greatest tragedy in modern science (in my eyes) is the loss of physics as a hard science, currently these guys are way off with the fairies and producing nothing of worth, string theorists are the worst. We'll see what the CERN guys manage to come up with, but right now the mathematicians have taken the ball and run with it. It has been said that physics has become too hard for the Physicists...
I am not trolling, I am quite serious about Physicists playing dodgey games with mathematics.
Here's a good example (credits to Nassim Taleb and his "The Black Swan" book) on the risks of extrapolation (of which curve fitting is one method): ...
- Based on previous experience, a turkey will confidently predict that he will wake up every morning be fed during the day and go to spleep in the evening. He can be easilly extrapolate this from the fact that it has happened every day of it's life. At some point before Christmas this turkey is going to have a big surprise
That since a dead clock is right twice a day, those two times cause the clock to work again?
No, the clock is right all of the time, it just shows local sidereal time and is often in the wrong place
Indeed. For example: 6 out of 7 dwarves aren't Happy.
Brain surgery - it's not rocket science!