#NullCore

Null results in scientific research are kind of like non-white people in Hollywood or women wearing clothes above a size 4. It’s true they’re the majority, but you wouldn’t know that from looking at big publications.

Here’s the thing about research: a lot of the time, you just don’t find anything new. If you were to follow the scientific method as impartially as the diagram in on your second grade classroom wall suggested, that’s a perfectly valid outcome. But when it comes to publication, papers with no significant results are more often tossed in favor of more striking, significant data with sexy little p-values* to flash around.

bias

Plus, even if null results make it into a journal, it’s unlikely that normal people will pay attention to them anyway. Have you ever clicked on a trending headline that said “Scientists ran an experiment–and you’ll totally expect what happened next!”?

Null results may not seem exciting or “groundbreaking,” but leaving them out makes for a seriously warped knowledge base. If you try enough times, you’ll get the occasional significant result showing that eating gummy bears prevents earthquakes (about one in 20 times, at a p ≤ 0.05 significance level). And if only those flukes get published, any literature review or meta-analysis is gonna conclude that California residents should adopt a gummy-bear-based diet (which also happens to be the theme of next week’s Dr. Oz show).

There have been efforts in some fields to counteract that bias with null results sections and registries, but that still doesn’t sound cool enough to catch on.

So maybe what we need is a super trendy nulls-only journal–any discipline is fine, but exclusively plus-sized p-values. And if you think that it won’t catch the attention of the science media machine, no need to worry: I’ve got some of flashy pop-science headlines to bring the hype:

Screen Shot 2016-07-12 at 4.06.06 PM

#NullIsTheNewSignificant


*No worries if Stats class was your nap time during high school senior year. In theory, a p-value is basically the probability of seeing results as extreme as yours just by chance, if there is no real effect at the population level. In common practice, it’s something that researchers really want to be small (sometimes through statistically questionable means).

 

Advertisements

Academia: a Fairy Tale

Once upon a time there was a princess who lived in a shiny white tower which stretched above a big forest called The Real World. She had entered the tower when she was young so that she could escape from the scary market forces and tax monsters in forest.

 

Of course not everyone could get into the tower. To get through the gates, she had answer a very long set of riddles sent from voices higher up.

Every so often, she would have the opportunity to climb one story higher in the tower if she followed the rules. And she did. She would answer more long sets of riddles. She would do a special kind of magic, turning very small ideas into very big books. She would create perfect illusions, appearing to know everything when she didn’t. She would learn to speak in peculiar tongues so that no one below her could understand. And of course, she would worship the voices above her. And so, over the years, she steadily rose higher and higher.

Each story of the tower was narrower and narrower, and fewer and fewer people would rise each time. Sometimes, people wouldn’t pass the tests, or the magic drained all their energy. And some would choose to leave. Either way, they would be sent tumbling down, scraping their skin as they brushed the thorny treetops of The Real World and bruising their bones as they found themselves at the very bottom.

But those who rose had their eyes on the tower’s tiny top floor. If you made it to that level, the prize was that you got to stay there forever and never leave.

The towers had windows where the princess could look down upon the people in The Real World. With each level she rose, the people became smaller and more distant. The higher voices said that the further away you were from people, the better you could understand them. This seemed true enough: she could see wider and farther than ever, noticing their numbers and patterns in ways she never did before. But most of all, she could see how small and faceless these people were, and feel bigger herself.

columbia princess

But one day, as she looked out the window, she could no longer see people, only a mass of tiny dots. She thought about the floors above her with fewer people around and tinier people below. She was starting to miss seeing faces.

She began to sit on the windowsill, thinking about what it might be like to live outside. One of the voices above warned her: “When you’re down there, you’ll be just as small as all those people. They won’t care about your crown or your magic tricks, and they won’t listen to your funny words. But if you stay here and keep climbing, I think you can make it all the way to the top.”

But as she imagined getting higher, lonelier, and further from the ground, she wondered if she should make the jump before it got too far.

Epilogue:

She hit the bottom and it hurt. The market forces blew away her crown and the tax monsters chased after her. She started crying “Take me back to my ivory tower!”



Yeah, I guess I’m feeling kind of cynical right now. 

You’ve Called the Grammar Police

If pedants ruled the world:

Hello? There’s two guys breaking into my house and I think they have—

I think you mean there are two guys.

Well yeah, and I think they—

You said “there is” two guys, which creates a mismatch in number between the subject and verb.

Look, I could care less about the mismatch

I think you mean that you couldn’t care less. “Could care less” would imply that you do indeed care quite a bit.

Right now I care about the guy that’s smashing my windows and—

Actually, it’s the guy who is smashing your windows. “That” is generally used to describe inanimate objects. Now there is some controversy surrounding the acceptability of using “that” and “who” interchangeably, but I tend to fall more in line with the traditionalists, who

LOOK, I’m not sure who I’m dealing with, but—

Whom.

What?!

“Who” is exclusively a subject pronoun, and you used it to refer to the grammatical object. “I’m not sure with whom I am dealing” would be the correct—

JUST HELP! They’ve got my husband and—

You mean they have your husband. . .

. . .

Hello?
Some people just won’t learn.

the_grammar_police_mug

Academia: Focusing on What is Important Since Socrates or Something.

 

*someone

Actual Lines From Actual Papers I Wrote

  • “While Carmen was intended as an exoticized depiction of the Other, Hey Arnold transforms it into a reflection of the self.
  • “In a way, this episode can be seen as advocating for the underappreciated role of the librettist, which is subordinate to both the composer and performer in the traditional production.”

Yep, I’m talking about this, football heads*:

Also, if you like awful puns . . .

Screen Shot 2015-03-29 at 5.20.51 PM

Sometimes I’m not sure if whether I’m taking this stuff too seriously or not seriously enough . . .

*Also, just wondering, am I the only one who spent several years of my early childhood thinking that Arnold was a girl?