Friday links: statistics on ecological statistics, a very Linux birthday, and more

Also this week: post-publication review is still for the scientific 1% (and its advocates remain in denial about that), the future replication crisis is here it’s just unevenly distributed, tenure policies vs. your forehead, Stephen Heard vs. laser pointers, maybe we should just move every species to Florida and get it over with, and more. Even a California condor unicorn link from Brian!

From Jeremy:

The latest excuse for why almost nobody uses commenting systems like PubPeer and Pub Med Central to do post-publication “review”, and why the vast majority of papers receive no comments: people are too busy to register for accounts. Yeah, people who feel too pressed for time to take five minutes to set up an account would totally take time to comment substantively and often if only they didn’t have to register. [eyeroll] And even now that we have PubPeer, which has long allowed complete anonymity without registration, it’s still the case that the vast majority of scientists do not comment, and the vast majority of papers receive no comments. I stand by my prediction that systems for commenting on published papers will never be used by most scientists or include comments on most papers, no matter how they’re designed. I’m not saying that’s a good or bad thing, I’m just saying that’s how it is and how it will be. If you believe otherwise, wanna bet?

Simply Statistics on why many fields of science have no replication crisis. Very interesting. Suggests that a replication crisis requires two key ingredients, both necessary but neither sufficient on its own: lack of strong basic theory, and reliance on controlled experiments. Yes, you read that right: there’s a cogent argument that, in the absence of good theory, reliance on controlled experiments is a bad thing. Aside: I’d quibble with one of the examples–it’s unfair to damn clinical medicine for lack of basic theory by citing the example of an NIH institute that was forced on NIH by Congress.

The growth of statistical sophistication machismo take your pick, quantified for ecology since 1990. Apparently, we reached peak ANOVA back in 2002; its usage has been declining ever since. Which is almost exactly when ecologists started using R. COINCIDENCE?! (ht Jarrett Byrnes, via Twitter)

Don’t dabble in the academic job market, meaning don’t apply just for the 1-5 jobs you think would be perfect for you. By a social scientist but more broadly applicable. (ht Dan Drezner)

Terry McGlynn on the absurdity of having the same tenure requirements for every field. If you weren’t aware that many small liberal arts colleges in the US follow this policy, and/or were looking for an excuse to bang your head on your desk, click through and have your eyes opened and/or head hurt.

This week in People Who Are Braver Than Me: Stephen Heard admits that he works (a bit) on vacation, not just because it’s sometimes necessary to meet a deadline, but because he likes it. At the end, he notes the importance of everyone finding their own balance in their own way. But if he’s unfortunate enough to have this post go viral, I’d give decent odds that that somebody will miss/willfully ignore that part and publicly shame him anyway. Personally, I’m more inclined to shame him for his choice of beach reading (Dick Francis?! Really?)🙂

Sticking with Stephen, he’s correct that laser pointers suck. But he omits the main reason they suck: they’re too hard to see and so don’t actually do the job they’re supposed to do: help walk the audience through the slide. If you want to point at your slides (and you probably will, needing to do so needn’t indicate an over-complicated slide), here are two much better options:

  1. Use a stick. One of those collapsible skinny metal ones is fine.
  2. Use your arm. Yes, it’s fine to just walk over to the screen and point at stuff! This generally is much more effective than you might think. It’s usually not a big deal that you’ll be standing in front of part of the screen while you point to another part.

Yes, you have to be able to physically reach the screen to use these options, but in most seminar and conference rooms you can.

Nothing a few hippos pythons couldn’t fix.

Happy 25th birthday Linux!:

The replies to the above are hilarious too. I liked this one:

And finally, Great Moments In Author Affiliations:

From Brian:

This is old but I just ran across it and its great. Its a PLOS paper by Weinberger et al that empirically tests common writing advice by looking at how frequently a paper is cited vs whether the abstracts follow the advice. Its worth reading the article, but the nutshell is the many pieces of advice about writing using short sentences and simple language lead to decreased citations but the advice about using evocative language and making clear novelty and importance claims increase citations. So go ahead; write complexly as long you write boldly.


3 thoughts on “Friday links: statistics on ecological statistics, a very Linux birthday, and more

  1. You’re right, Jeremy, most laser pointers are hard to see – but I’d argue that isn’t a reason laser pointers suck; that’s actually a reason they suck (b>less than they would if they actually did what the user presumably wants! If you can see them, it makes things worse, not better. But I’ll second your preference for a stick, or for your arm (referred to in my post as “the pointer that evolution hung from your shoulder”). Thanks for linking.

  2. laser pointers are designed for cat owners…once time, with a broken foot, I had to use crutches to point. I must say that was pretty effective🙂

Leave a Comment

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s