Профиль

Yes, and anyone intuitively understands that you need a better method. So you can also use this to explain why hypothesis testing is one of the most important discoveries mankind has made - much better than coin flipping or random guessing.

But I like the main point. Next time someone asks me to explain what a p value is in a single sentence, I will ask them to first explain to me what the color red in a single sentence :)

We compute a number that should be higher or lower than a criterion. If the effect size is larger than a critical value, it the t-value is larger, or a p-value is smaller, you can say there is something because the long run probability that you are fooling yourself is small enough.

Agree with everything there. Except maybe that we typically do not even want to explain what p-values are. We want to explain what a testing procedure does: It is a statistical method to limit how often we say something is going on, when nothing is going on. If anything, explain alpha is that limit.

There is no need to require your PhDs to do registered Reports. They are your PhD's! You let them decide if they want to do them. They would for starters need to be able to design a good confirmatory study. That is already rare enough to mostly not do RRs

I am not interested in convincing you about Registered Reports. You will soon retire and die. I am mainly interested in convincing your (or in general, the) PhD students directly. That is going well enough.

But surely, it is obviously better to move to journal 2 after the crappy peer review before data collection? So your argument is mute.

It is so obvious he you just work through the reasoning, I will leave the proof to the reader.

OK, but I realize your concern gets things completely wrong. It is infinitely better to do registered Reports given your concerns!

I am currently working on a major addition to help researchers share data and code in a FAIR and reproducible manner. It's an incredibly exciting project that I strongly believe has immense potential.

Do you mean disadvantage, or hypothetical disadvantage? I have never seen this materialize in a Registered Report. Multiple reviewers and an editor would need to remain unconvinced by your rebuttal that an idea is bad. And even if this happened - it is still worse to get this AFTER data collection?

;)

Check out Scheduled Review at PCI Registered Report: rr.peercommunityin.org/about/full_p...

Sorry, I don't know what to do with this comment. Metascience is strongly anchored in studying the reward structures. You could say that is the core of the field. Many are social psychologists, like myself. I don't see any real insight in your post. Can you clarify?

We have solved this through out code of conduct. Your work should be be influenced by personal, political, etc biases. Do you really want to control who gets to fund scientists? You will just end up making science in your country more political, speeding up the ongoing decline.

Oh yes indeed. I only heard people complain about how horrible it was.

because it clearly improves the quality of science. No one here is worried about bad actors having secret agendas. I feel for Americans that they need to waste their cognitive resources on such ideas. I understand it. But do not expect me to support the quatsch about my field.

You are right that this is mainly in the USA. If exactly the same points and criticisms are made in Europe, the cause can not be the messed up political situation in the USA. By all means, study who wants what. But everyone with a brain needs to accept that in Europe governments fund open science >

Several of my PhD students are more principled about fighting the system than I am, so by all means, ask! They also have a bit more time, typically, and they are perfectly able to do it!

Hell, the fields was saying there is a crisis 50 years ago! Without the political situation in the US being so immensely fucked up that Americans can no longer think straight! rips-irsp.com/articles/10....