On the subject in the title: Sample size calculations, read backwards from the published number Working notes rather than a conclusion.
Sample size calculations — I have the observation and I do not trust my interpretation of it, so I am posting the observation and holding the interpretation back.
Numbers, method and the conditions under which they were collected are below. Interpret them however they warrant.
The opening post put the caveat in the right place and I want to underline it.
Marking my uncertainty on Sample size calculations explicitly. I am confident about the direction, much less confident about the size, and not confident at all that it generalises past the case in the first post.
I read post #4 twice before replying, because I had assumed the opposite.
Absolute numbers, not just relative: a 30% relative reduction tells you the ratio but not the practical magnitude. The event rate in each arm and the difference between them tells you how many people benefit.
What I would want before treating Sample size calculations as settled: the method, the sample, and whether anyone tried to find the opposite result. Two of the three are usually missing.
Agreed, and I will stop repeating the version of this I had been repeating.
The question underneath Sample size calculations is usually "how would I tell?" rather than "what is true?", and that one has a method attached to it.
Write down what you would expect to see under each hypothesis before you collect anything. If they predict the same observation, collecting it will not help.
I read post #9 twice before replying, because I had assumed the opposite.
Risk of bias: structured appraisal of internal validity. Key things to assess: randomisation method (was it truly random or could someone predict the next assignment), concealment (could randomisation be subverted), blinding (who was blinded and why or why not), completeness of outcome reporting.
Taking Sample size calculations seriously for a moment rather than deflecting: the honest position is that the community has observations and no controlled comparison, and those two things support very different sentences.
Confirming post #11 from a second method, which matters more than confirming it from a second person.
Composite endpoints should be read component by component. A composite driven entirely by its softest component is a different finding from one where the components move together.
Grateful for the specificity. Vague answers to this question are what sent me looking.
Reading back through the Sample size calculations threads from last year, the same three questions come up every time and only one of them has ever been answered properly. That seems like a documentation gap rather than a knowledge gap.
Where I part company with post #11, and it is a narrow parting.
Number needed to treat is only interpretable with the duration attached. The same NNT over one year and over five years describes very different clinical situations.
Sample size calculations is well covered in the tag pages, and the older discussions are better than the recent ones because they were argued out properly. Worth twenty minutes before adding to this one.
A treatment-policy estimand asks what happens to people assigned to a strategy, including those who abandon it. A hypothetical estimand asks what would have happened had everyone continued. Both are legitimate and they give different numbers.
Adding the caveat now so it does not have to be extracted later.
The practical version of Sample size calculations is three sentences long. The rigorous version is three pages and reaches the same conclusion with the conditions attached.
Taking post #20 at face value and following it one step further.
Absolute and relative effects answer different questions. Write down the event rate in each arm and the difference between them; everything quotable is derived from those two numbers.
Take the reasoning and check the arithmetic; I do not always get it right.
Seconded. It reads as careful rather than confident, which is the right register.
Building on post #24 rather than restating it.
Absolute numbers, not just relative: a 30% relative reduction tells you the ratio but not the practical magnitude. The event rate in each arm and the difference between them tells you how many people benefit.
I looked this up rather than remembered it, which is the right order.
Risk of bias: structured appraisal of internal validity. Key things to assess: randomisation method (was it truly random or could someone predict the next assignment), concealment (could randomisation be subverted), blinding (who was blinded and why or why not), completeness of outcome reporting.
A note on how Sample size calculations gets discussed rather than on Sample size calculations itself: the confident posts get the replies and the careful ones get ignored, and the careful ones have been right more often.
On post #26 — agreed on the reasoning, with one qualification.
Discontinuation handling is the methodological detail that most changes a result and gets the least attention. Read how missing data was imputed before reading the effect size.
That has been true for the cases I have seen and I have not seen many.