Felix S. Bethke
banner
felixbethke.bsky.social
Felix S. Bethke
@felixbethke.bsky.social
Political Scientist at Peace Research Institute Frankfurt (PRIF, @priforg.bsky.social)
Tweets on DataScience, Econometrics and African Politics
Website: fbethke.netlify.app
Kürschners Volkshandbuch. Das hat alles was Du brauchst. Aber bitte mach dann die Y-Achse mit Nullpunkt :D
December 4, 2023 at 8:00 AM
My favorite take on this LaTex vs. Word debate is this one:

arxiv.org/pdf/1003.608...

Check page 4 the technical note says it all.
November 17, 2023 at 11:31 AM
Hi Jay,
thanks for sharing these infos here and on your website. Do you have any updated data yet on the importance of pro-Palestine protests relative to pro-Israel protests in the US, i.e. freq. and size of events? Last info on this I could find was from October 17 on your blog.
November 13, 2023 at 7:00 AM
Wow, die Ziele sind wirklich niedrig und dabei:
"Als pünktlich gilt ein Zug mit weniger als sechs Minuten Verspätung. Ausgefallene Züge werden in der Statistik nicht berücksichtigt. Auch verpasste Anschlüsse gehen aus ihr nicht hervor."
November 10, 2023 at 3:51 PM
Reposted by Felix S. Bethke
In other words, it is not really possible to have observed higher replicability than we did.

The evidence provides proof-of-concept that high replicability is achievable. We can't, however, say the extent to which each practice contributed to replicability.
November 9, 2023 at 5:13 PM
Reposted by Felix S. Bethke
With a total of 16 new discoveries, 16 self-replications, and 48 independent replications, we found high replicability. Independent replication effect sizes were 97% the size of the confirmatory findings.

On the "same direction, p<.05" benchmark, 86% replicated, higher than expected based on power
November 9, 2023 at 5:11 PM
I have good contacts with Lucid in Germany, related to survey participent recruitment. But this is probably not what you need. Email me at bethke@prif.org if you need the contact.
November 8, 2023 at 8:19 PM