Here's the question page.

Franklin Veaux
Written Mar 13, 2017

Correlation does not show causation. This is the #1 thing people get wrong over and over. “I took this homeopathic remedy and felt better. See, homeopathy works!” “MRI scans of heavy porn users shows brain damage. See, porn damages your brain!” “Increases in ice cream sales are strongly correlated with drowning accidents. See, ice cream causes drowning!” “My baby got a shot and was diagnosed with autism. See, vaccines cause autism!” “Sales of organic produce are very strongly correlated with autism. See, organic farming causes autism!”

It is okay to say “we don't know yet.” “If there is no god, what caused the Big Bang?” “We don't know yet.” 10,000 years ago, someone could say “if the sun is not a god, then what is it?” and the only real answer was not “you're right, the sun must be a god because we don't know what else it could be.” The right answer was “we don't know yet.” Now we do, and the answer turned out not to be “a god.”

How to understand p values. If I say to you “Placing a pickle on your nose gives you the magic mind-control power to affect a coin toss, look!” and then I place a pickle on my nose, wave my hands in the air, and say “by the Power of the Pickle, I hereby declare I will throw heads!” and I toss a coin and it comes up heads, I have just shown that a pickle on my nose gives me the power to control a coin toss (p=.5). That means there's a 50/50 chance that the null hypothesis is correct; the pickle has nothing to do with it.

If I did this to you, and I tossed heads, you'd say “Oh, c’mon, really? There's a 50/50 chance you'd toss heads anyway. Throw the coin a whole bunch of times if you want me to believe you.” Yet many people will accept results that are quite likely due to just pure random chance if they confirm what that person already wants to believe.

Scientists are not conspiring to lie to people or hide the truth. Anyone who's ever worked with real research scientists know how absurd that is. Science is not cordial. Science is viciously, ruthlessly competitive. You want to know what peer review is like? Imagine the meanest mean girl in your high school on her absolute worst, most conniving day. Now give her a Ph.D. in your field and some level of control over your career. That's peer review. Scientists love finding flaws or faults in other people's work.

It is possible to buy off one or two scientists. It is not possible to buy off all of science.

In the 1920s, research was already showing that cigarette smoking caused cancer. By the 1970s, two scientists getting paid by tobacco companies said it didn't; everybody else said it did. The evidence was that it did.

Today, one scientist and one science philosopher getting paid by organic food companies say GM food is dangerous. Everybody else says it isn't. The evidence is that GM food is not dangerous.

You can't buy off all science. Not even oil companies have that much money. Look carefully at where the consensus is; that's usually where the evidence is.