if you were to travel by train through Denmark, there's a fair chance you would pass through Middelfart

This makes me think of Terry Pratchett's Hogfather

I attended a course on clinical RCTs last year and CACE was mentioned but it did seem like an acquired estimand/taste

The estimands framework: a primer on the ICH E9(R1) addendum - PubMed Estimands can be used in studies of healthcare interventions to clarify the interpretation of treatment effects. The addendum to the ICH E9 harmonised guideline on statistical principles for clinical trials (ICH E9(R1)) describes a framework for using estimands as part of a study. This paper provide …

I think the terminology is also evolving somewhat - that's not to say PP and ITT are irrelevant terms, but I find this paper highly useful in articulating what one wants to estimate, and ITT/PP can probably cover several different estimands pubmed.ncbi.nlm.nih.gov/38262663/

it's not as if there is anything special about 90, we do it for 50 (half three) and 70 (half four) too. Also, 60 and 80 are three and four scores.

(To me, the article makes it look as though the control arm is no vaccination at all.)

I don't want to defend the trial - the vaccine should be rolled out ASAP, so the money should be spent on that rather than research. However, as far as I can tell, the comparison is between vaccination at birth and vaccination at age 6 weeks. Or have I misunderstood something?

The one on day 12 seems to be even weirder than the solution suggests, I think. Not only do the SDs end in 0 or 5, as far as I can tell
mean + SD = max, and
mean - SD = min

I use this one: Mary's virgin explanation made Joseph suspect upstairs neighbour

The careful reader (who knows the approximate absolute risk) will see this even if only the RR is presented, but I also think many would look at 1.25 and think this is important.

I agree in principle, but I think this ties back to the comment about vibes. I discussed results with a student today, RR of 1.25 RD of 0.2% (as I recall). The RR supports her hypothesis that something is going on, but the RD suggests it is clinically irrelevant in the given context.

"Normalized incompetence" seems to sum up my day-to-day!

Linear algebra, or as it was known among the physicists at my university: the most import subject you will ever forget

phdd level intelligencee

I can't help but wonder, if there was a group of people with a better than average immune system would they actually benefit more from (typical*) vaccines? Not that this in any way makes him right about anything.

*I don't know much about vaccines or how they work, so unsure if "typical" makes sense

Putting myself out there a bit. Honest request from an open-source developer:

Can I please ask you to encourage people you know to stop with the "any updates on this?" discussion post? Every post like that genuinely makes me die inside a little bit.

I'll try to explain in this thread. 1/

We should introduce the term “real human researchers” (RHR) to go with other nonsense phrases like “real world evidence”

If that case, I suggest you take the car

figure showing size of brain against age, with the age-scale highly non-linear

for the first point, I think I have seen small/average/large for gestational age being sorted as average/large/small (both on an axis and in legends). For the second it could be something like this (www.flickr.com/photos/65802...)

likewise, if values of a continuous variable are treated as if categorical so that distance between values are the same regardless of the actual distances.

one of those figures where something is plotted within levels of an ordinal variable and the ordinal variable is sorted alphabetically (e.g., "high" "low" "medium") rather than by the natural order.

today's useful tip

A mugshot of Feathers McGraw and a picture of Feathers McGraw disguised as a chicken, with captions likening the two to observational studies and target trial emulations

I agree, the framework is a good (least crappy?) solution for observational studies, but the term TTE itself is like Feathers McGraw's rubber glove. (Some) Reader think they see a friendly chicken when they are in fact staring at a villainous penguin

Thank you for the swift reply - at first I did not realize how close the book and the package (and by extension the github page) are to eachother, but it makes sense to have it all in one place. I will report there if I find anything else :)

R code for a hypotesis test and the result

In the same chapter there is also a 95% CI for a ratio going below 0 - is that a bug or a feature?

R-code and result about hypothesis tests for ratios

Hi, just started reading your book - impressive work. Do you have a place for reporting errors etc. specifically for the book?

I would probably expect that the test below (Chapter 4) was for ratios being equal to 1, but it appears that tests are for ratios being 0. Am I missing a point here?

yep - often mentioned in the stats group I work in. We don't get it, and seeing it has been a long time we have not got it, I start to think it is simply because we are not very smart when everyone else apparently gets it

Dog only throw no take frisbee meme First panel: self-correction please Second panel: no correction Third panel: only self-collection

I’ve seen situations in which people try to correct the scientific record and then critics act like that was superfluous or just not the right way to use one’s energy because “science is self-correcting.”

This just came to my mind

but centuries vary in number of leap years too - an let's not forget those leap seconds

"ugler i mosen" is peculiar - I think it's from Denmark where it was originally "ulve i mosen" (wolves on the moor), but as wolves became extinct in Denmark it became "ugler i mosen". Norway must have taken the written word rather than the meaning (I believe it should have been "ugler i myren" then)