Kaspar Rufibach (@numbersman77) header
Kaspar Rufibach (@numbersman77) profile picture

Family & sports person. Biostatistician for @roche in @BaselStadt. @numbersman77@mstdn.science

Meiringen, Schweiz
Joined July 2017
Photo by Kaspar Rufibach (@numbersman77)Photo by Kaspar Rufibach (@numbersman77)Photo by Kaspar Rufibach (@numbersman77)Photo by Kaspar Rufibach (@numbersman77)Photo by Kaspar Rufibach (@numbersman77)Photo by Kaspar Rufibach (@numbersman77)
Thread to save my longer threads for (my own) future reference.
2
4
15
1) Why do we run group-sequential trials in drug development? 2) How does the effect we power at relate to the effect(s) needed to stop? 3) Is stopping such a trial early (like the one for the Pfizer vaccine) "cheating"?
1
25
9
55
So group-sequential designs reduce expected number of events needed and provide valid inference in reasonable cases. This all within the framework of hypothesis testing, as required by Health Authority guidelines. I hope this thread is useful. Comments welcome! The end.
5
10
I could not agree more to both points!
It’s a common misconception that real world data necessarily reflect the real world & are more representative than other data. It’s another common misconception that it needs representative pts to determine treatment effects.
2
464
1/2 Upcoming seminar of the Basel Biometric Society: Quantification of risk: ask the right questions or time to apply the estimand framework to safety! Speakers from industry + regulators will give overview of current thinking and share recent development in safety evaluation.
1
6
972
2/2 The event will take place on the afternoon of 12th April in a hybrid format, with face-to-face attendance on Novartis Campus in Basel. Agenda: baselbiometrics.github.io/ho… Registration: docs.google.com/forms/d/e/1F… Please RT!
3
352
1/3 Time to bust some myths about use of R and open source software in general for submissions to the FDA! When I joined pharma in 2012 I admit I was surprised about how inert pharma reporting systems were, and how little was made use of capabilities such as, e.g., R, sweave,
1
8
2/3 and later markdown. I am impressed to see how over time capabilities have been recognized and that several companies invested a massive effort into rebuilding the entire reporting pipeline up to regulatory submissions.
1
2
Same here: @numbersman77@mstdn.science
This Post is from an account that no longer exists. Learn more
1
Kaspar Rufibach retweeted
We are very excited about our awesome keynote speakers for #rinpharma Nov 8-10 @sciencealice (pathos.com), Catherine Igartua (@TempusLabs), Robert Gentleman (@harvardmed) & Ross Farrugia (@Roche)! hopin.com/events/r-pharma-20… #rstats #pharmaverse #OpenScience #opensource
5
7
Roche is looking for statisticians in clinical development in Basel. Come work with us - @Roche is a great company to work for (I have been there for >10y and still very happy!) and we are a cool bunch of folks in Basel! linkedin.com/jobs/view/32284…
1
1