jdushoff.bsky.social
Theoretical biologist, recreational mathematician, anti-fascist*.
* I had planned not to be political here, but when circumstances change, decisions sometimes have to change.
155 posts
913 followers
113 following
Regular Contributor
Active Commenter
comment in response to
post
I agree and sympathize.
For now, get a new number, and don't give it out to anyone you don't know. It's probably easier than you probably think.
comment in response to
post
Not worth the price, though. And I live in Canada.
comment in response to
post
"Ask the lawyers who I selected on the basis of regularly saying things that I want to hear"
comment in response to
post
Yes, I do. It's an incantation I added to a Makefile many years ago, probably on the advice of @bbolker.bsky.social.
comment in response to
post
I don't copy libraries, but I do run update.packages. is that still dangerous?
comment in response to
post
What about "entropic"? Awkward, but possibly closest in meaning.
comment in response to
post
"merit-driven". You can define it in the body of the grant as corresponding to a large Shannon and/or Hill index. You'll sneak past the censors and get a wink and nod from reviewers. I'm trying to figure out whether I'm joking here or not.
comment in response to
post
Graham thinks he's being funny... not worth our time.
comment in response to
post
Next they're going to get Bukele to tattoo him.
comment in response to
post
I find it very hard to shift my mind-set into their bubble (I guess I should admit we're in a bubble, too, although we seem more sane) -- but I guess that Graham thinks he's being funny.
comment in response to
post
When I read that line, I suddenly realized I was on to something special. I think I put the book down for a moment, it hit me that hard.
comment in response to
post
4/2025 is correct. I set the problem for this month and this year.
The other one is equally beautiful. Try factoring more.
comment in response to
post
Thanks for this clarification. I am pleased to be able to share with you that your gofundme has already raised over 30,000 Canadian dollars. Hopefully that will be sufficient to tide you over, and maybe you will find it in your heart to help some others. I will stick with established charities.
comment in response to
post
I feel like the courts are expected to understand that the regime is playing a game of giving them the bare minimum of respect to allow them to save face, and expected to feel grateful the regime doesn't just say "lol, no". And worried that they will soon.
comment in response to
post
I wish you well, but currently am only donating to known charities.
comment in response to
post
You're running out of time to answer this! For a reason which I will not divulge. You may also be interested in 1/975 + 1/1053.
comment in response to
post
"I decline to call out the most powerful man in the world for outrageous abuses of power because I know people who are biased against him and criticize him _more_ than they should."
comment in response to
post
We'll have to disagree about that, too
comment in response to
post
I was thinking of clinical trials. I thought that was clear (what is non-inferiority in a medical setting?).
And of _course_ it makes sense that preregistration is now "separate". Wish you had said so earlier!
This has been fun, but I'm out, thanks.
comment in response to
post
Actually, I said the part about a scientifically determined threshold right here.
comment in response to
post
As I said elsewhere:
* Yes, there needs to be a step where the practical significance is established scientifically
* No, this is NOT the last step in deciding clinical sufficiency; it is done in advance of data collection, and the binary statistical determination is the last step.
Is that OK?
comment in response to
post
You need to keep going.
comment in response to
post
That's clever. My answer was long division. Took me a second to figure out your way. Is that something you were taught, or did you come up with it on the spot?
comment in response to
post
I agree it would be good to have better tools. I've agreed with a lot of your points, and even made some of them independently. The question here is whether it's time to abandon NHST completely. Sorry that F6 (meaning, in this paper) was not clear to you; I gave that same example before.
comment in response to
post
I have no idea which of your reasons you think applies. Indulge me, though: Are you saying that the final step in making a binary decision about sufficiency of clinical data should be analyst judgment?
comment in response to
post
I'm not sure. I agree that it should not be made without a scientifically (not statistically) determined effect threshold. But what do you think of non-inferiority testing, where the threshold is picked first and then the binary stat is the final piece of the decision?
comment in response to
post
I mean, _maybe_ smart people can do better than the proxy in every single case. But that still doesn't make this approach absurd. The simplicity appeals to me. In my mind it's conceptually the same thing across cases: evaluate fairly whether you're seeing clearly (using CIs for that when practical).
comment in response to
post
This makes some sense, and is standard (thus avoids adding “researcher degrees of freedom”), and reduces time spent interpreting noise. If CIs could be constructed (for the difference, not the ellipses), that would be better. But nothing here is absurd, and it nobody thinks H0 might be true...
comment in response to
post
Let's just _assume_ the difference between ellipses in F6 is of biological interest. The authors did not find a way to construct a confidence interval for difference, so they are using its "statistical clarity" (P<α) as a proxy for saying that the change is clear enough to be evaluated …
comment in response to
post
I'm so confused here. I've repeated that I prefer CIs to the point where I literally felt I was being silly about it! Sometimes binary decisions do need to be made (a point that I agree with, but picked up here from you). I will add some thoughts about Ben's example as well...
comment in response to
post
I commented on your draft article because you asked me to, but now I'm wondering if that was more about postponing your need to think about what I had already said than about interest in what I might say.
comment in response to
post
I'm honestly wondering if you bothered to "wade through" my 300-character post on this. Or bothered to process my suggestion that NHST is not "absurd" if it's a proxy for clarity, after what feels like many tries. I'll wait for a sign of non-trivial engagement before trying to reach you again.
comment in response to
post
The point is practicality. I think it's sensible, and am happy to discuss. The fact that it's simple and accepted makes it attractive for applying and sharing with others. To beat the dead horse, I agree that P values are overused, and often misused, and that CIs are better when available.
comment in response to
post
I don't want to throw away information, but I do sometimes want a binary approach. We agree the decision needs to be made, and we agree that CIs provide useful information. Non-inferiority constructs a NHST not by throwing away scientific judgment, but by making the judgment before seeing the data.
comment in response to
post
You may or may not remember that I agreed with you about this in an earlier thread. I always prefer CIs to P values, when the CIs are practically obtainable. Ben Bolker gave an example that I commented on where they don't seem to be. Other cases can also arise. You did not respond there.
comment in response to
post
I think you know I don't think acceptance proves validity, and I don't think you can find evidence that I'm arguing that way. This feels like laziness or abuse, to be honest.
Other than the possibility of bias or errors, what is your specific objection to the non-inferiority approach?
comment in response to
post
Struggling to understand. I didn't worry about the hypothetical user because it was in the section about whether we actually accept the null hypothesis -- which we agree about. But now it doesn't make much sense to me. Are you saying we should only use methods not susceptible to bias or errors?