Noah Simon

@DeepDishEnjoyer Reminiscent of P(no heads in n flips) from a coin with uniform prior on p (a la bayesian billiards)

@StatsSimon Exactly right

Deepseek gets this rather simple problem wrong. Are you smarter than Deepseek?

@DeepDishEnjoyer (I assumed you dropped a final flag; without that it is 2/(n+1) )

@DeepDishEnjoyer I think the answer for n flags is 2/n? (By exchangeability of flags/ordering, and linearity of expectation)

@DrJesseMorse @SlinkECasey I read the studies you posted; they seem like interesting preclinical work, that warrant followup. To pretend they abrogate the need for chemotherapy seems misguided. Are you involved in clinical research in oncology? (2/2)

@DrJesseMorse @SlinkECasey Are you really claiming that the primary reason that oncologists use chemotherapy is to make money, and not the mountains of evidence that for the majority of cancers chemotherapeutic agents are extremely important as a first-line therapy…? (1/2)

Ivermectin and Fenbendazole have been in the media recently. Especially as it pertains to treating cancer. What does the data show? Well I’ll show you. But first, what if we are asking the wrong questions. Ivermectin and Fenbendazole are drugs used to kill parasites in the body. What if parasites & myocotoxins (mold) are playing a role in autoimmune disease and the development of cancer? I specialize in heavy metal toxicity & mold/mycotoxin poisoning. These destroy your mitochondria and lead to a compromised immune system. Toxicity and inflammation are the keys to disease. Just like many antibiotics are anti-inflammatory, just because a medication is classified as an antiparasitic or antifungal doesn’t mean it doesn’t have other properties and benefits. Here are some articles to support Ivermectin’s anti-cancer benefits: pmc.ncbi.nlm.nih.gov/articles/PMC75… pubmed.ncbi.nlm.nih.gov/37171616/ pubmed.ncbi.nlm.nih.gov/36975598/ pubmed.ncbi.nlm.nih.gov/36503300/ Here are some articles to support Fenbendazole’s anti-cancer benefits: ar.iiarjournals.org/content/44/9/3… pmc.ncbi.nlm.nih.gov/articles/PMC35… pmc.ncbi.nlm.nih.gov/articles/PMC94… ejgo.org/DOIx.php?id=10… And likely many more. It’s EASY to say something doesn’t work but when you actually spend time to look for the data, you’d be surprised what you’d find!

@edwardhkennedy Charles stein actually proposed the crux of TMLE in “efficient non parametric testing and estimation” (1958) — last paragraph of section 2. Which is absolutely wild.

PSA - the main ideas behind “causal ML” and “double machine learning” go back at least 40 years Here is an estimator from a 1982 textbook that today would be called double machine learning or something similar

@Sarah_Explains @realmayo112 @USA_Polling We also have a) primarily domestic debt which makes hyperinflation much less likely and b) the reserve currency, so it would be much easier for us to service foreign debts. (I assume you know this, but perhaps it can help relieve some ignorance of those you are responding to)

holy shit he's actually stupid

@karlrohe Exactly! It’s a really devious “puzzle question” to ask, since you can even give the answer, and just ask for the (impossible) justification !

@StatsSimon whhhhaaat

What about n points on the sphere instead of the circle?? x.com/picopaco17/sta…

@karlrohe It would be awesome if there was a simple/slick argument for it, but the route I have seen is actually a fair amount of work! mathpages.com/home/kmath327/…

@karlrohe I believe the expected number of points you need to draw on a sphere until they don’t all share a hemisphere is exactly 7; and I think the probably that 6 share a hemisphere is, coincidentally exactly 1/2.

@karlrohe My guess is HT strat is superior- it is the sum of negatively autocorrelated indicators; HH is positively autocorrelated and has at least a slightly longer right tail. (Both have the same mean) so i imagine that tail forces the bulk to shift left

Haven’t solved it… but find the independence Eg break it up into 50 chunks of 2 tosses. 50 draws from Multinomial on 4 types. Independent. Those are equal and fair. Then, you can shuffle them in any order. So, string them together, by picking one at a time, without replacement

@karlrohe I think you’re swell

@dmbean85 I majored in statistics because I wanted people to like me

First: you think statistics is about science and numbers Then: you become enraptured by models and math, forgetting the science. Finally: you see through the models and math, to see the underlying subject once again, this time clearer

@jsm2334 @GidMK Cetuximab in colorectal too I believe (though there was a bit of posthoc analysis)

@GidMK Don’t have the trials in front of me but: Subtype driven breast cancer therapy Immunotherapy for melanoma Car-T therapy

Does anyone have a good example where precision medicine (however defined) actually resulted in a demonstrable clinical benefit in a decent trial?

@alexkyllo 1) this is sometimes referred to as the “mean/variance relationship” (you can use a score test to partially mitigate this — score test in this case is the chi-square test), 2) this piece can be calculated using the berry-Esseen CLT

@alexkyllo Two ways to think about this: 1) the variance of each sample proportion blows up in the tails, so the estimated variance is a poor proxy for true variance; 2) the error from CLT/normal approx has a term that looks like 1/(np(1-p)) which is large near 0/1

I recall seeing something on my TL about the reason why a statistical test for a difference between proportions very close to zero (e.g. a 50% increase from 0.0002 to 0.0003) is problematic, but I can't find it. Anyone know?

@RuiWang97 @Jake_Elder52 Good question! Answer is a bit subtle --- I am pretty sure for any correctly specified parametric model (that is then marginalized to estimate a treatment effect) this will hold. However, linear regression is also robust to model misspecification.

@StatsSimon @Jake_Elder52 I am wondering if it’s a general rule or it only holds in linear model (i.e., including precision variable could reduce variance.

Is there a name for var that causes Y but no causal relation to X? And what does a variable that causes Y but no relation to X do when controlled for. Confounders should be controlled for but what if C only causes Y but not X? From Wysocki et al. (2022)

@krishnanrohit Absolutely no offense to Mark (everyone has to start somewhere) but this is the beginner division. Winning the beginner division can (very reasonably) be a personal point of pride. But it’s odd to use as a talking point for how amazing someone is.

Say what you will, Zuck is pretty amazing. entrepreneur.com/business-news/…

@alexkyllo I do remember those "revolutions" fondly! (and our roll!) I also quit in 2020 with covid, and then baby happened. And then I severely herniated a disk in my back powerlifting in my garage :(. We will see if I ever return! I hope your return is fun and painless (for you ;) )

@StatsSimon Do you still train? I remember we competed like ten years ago as purple belts, you were really good! I quit training in 2020 because of COVID and babies but I'm planning to get back into it this summer.

It either has to be a class or team sport so that it's social and scheduled, or it has to be something that gives you measurable progress *and* a dopamine rush.