This book has been in continuous print since 1954.....................
This book has been in continuous print since 1954.....................
86.3% of statistics are made up on the spur of the moment.
That’s my claim and I;m sticking with it!
“There are three kinds of lies: lies, damned lies, and statistics.”....Mark Twain............
Find your favorite fallacy. How about, hard statistical evidence followed by poorly supported assertions that have nothing to do with the evidence. That’s bullying, IMHO.
Yep - it’s all about how you present the data. I never see confidence intervals, p-values, etc in any news reporting. Mainly because the only thing the idiots really understand is gross percentages...which can be fudged by using the other values.
Firat step, get a box.
(Ignorance is bliss!) Solution: More epidemiology on how people collect, manipulate, analyse, communicate and consume data.
As Shakespeare said, "For all the rest, they'll take suggestion as a cat laps milk. They'll tell the clock to any business that we say befits the hour."
You mean that four out of five dentists DIDN'T really recommend Dentyne?
-PJ
Reality is too complex to model with numbers.
A famous example from WW2 was American statistician realized the German industry was continuing to grow despite massive bombing raids. This caused the military to switch from bombing factories to bombing people which strengthened German’s resolve to fight on. The reality was that weapons being made in the new German industry were generally crap and what the bombing raids were doing was reducing the quality of German arms which in turn reduced German fighting effectiveness. But this couldn’t be modeled statistically so it was ignored.
The most effective part of the US bombing campaign came in the last 6-8 months of the war where we targeted Germany’s transportation grid instead of its factories or people. The results of attacks that couldn’t be modeled by statistics. These attacks caused the Germany industry to grind to a halt as rare materials and food we were no longer able to get from point A to point B. If we’d listened to the air force generals urging attacks on the transport grid instead of the bean counters the war would have been over in late 1944.
Moral of the story: Never trust a bean counter.
My youngest Daughter double Majored ... she Interned at Ford and at that time was a Theoretical Math Major, they told her she needed a salable Degree and recommended Statistics so she made that her Primary but she Loves Theoretical Math and just does Statistics to pay the way cause Dad told her “NO LOANS” and Dad is 3 outta 3 (3 kids w Degrees and 3 kids without Student Loans)
One of my favorite sayings:
“If you torture numbers they will confess to anything.”
In Signal and Noise, Nate Silver admits the truth. BIAS.
Statistics are based on a population, a sample, on collected data. There is bias in which data to collect and which data to ignore. There is bias in the weight given to each piece of data collected. There is bias in refusing to admit/recognize the bias. There is bias in refusing to admit what you do not know. There is bias in refusing to admit that you don’t know what you don’t know.
Then there is bias in believing the data. A famous Artificial Intelligence company did a study of immunizations. It believed in advance that immunizations were useful. When accurate math did not prove the pre-conceived bias, they adjusted the denominator to make it fit their bias. They did not do this to intentionally lie. They did it because they knew that the correct answer could not possibly be correct because everybody knew immunizations were good.
They then recommended more immunizations based on their failure of 5th grade math.
Their original math was correct but their understanding of the raw data was seriously flawed. Sick people go to the doctor more often than healthy people. When people go to the doctor, the doctor always pushes a flu shot or whatever immunization is available. So invariably sick people get more shots than healthy people. Naturally, From the thing they got a shot for, sick people get sick more often than healthy people, despite the shot.
But high paid AI gurus with PHDs don’t know what your uncle knows.
I think the most common thing I am seeing is applying statistical analysis to a dataset then applying statistical tests to the processed data rather than the original dataset. Of course it is going have a positive result to what ever you are trying to prove or disprove.