Harlan
harlanhappydog.bsky.social
Harlan
@harlanhappydog.bsky.social
Reposted by Harlan
There is a new release candidate 2.37.0-rc3 for CmdStan / Stan. If you have big Stan models, help us to test the release candidate by compiling and fitting your models (I already caught one bug with my birthdays models). See installation instructions at discourse.mc-stan.org/t/cmdstan-st...
CmdStan & Stan 2.37 release candidate
After a long delay (due to developer travel and some tricky new issues), release candidate 3 for Stan 2.37 was released today. Besides these resolved issues, the highlight change in this RC is unfort...
discourse.mc-stan.org
August 21, 2025 at 7:57 AM
Newly published discussion in Biometrics about a new Bayesian method for hybrid control arms. The LEAP approach shows great potential to increase the efficiency of clinical trials. see: lnkd.in/gGbvNTAK
October 3, 2024 at 3:03 AM
"When can a credible interval be defined and what does it mean?"

A webinar tomorrow with myself and Paul Gustafson hosted by the ISBA -

us06web.zoom.us/webinar/regi...
Welcome! You are invited to join a webinar: Bayesian Analysis discussion webinar (Campbell & Gustafson). After registering, you will receive a confirmation email about joining the webinar.
Discussion of the paper by Harlan Campbell and Paul Gustafson Link to the paper: https://doi.org/10.1214/23-BA1397
us06web.zoom.us
October 1, 2024 at 10:08 PM
Webinar on the Discussion Paper of Bayesian Analysis:
“Defining a Credible Interval Is Not Always Possible with “Point-Null” Priors: A Lesser-Known Correlate of the Jeffreys-Lindley Paradox”
by Harlan Campbell and Paul Gustafson on
Wed, Oct 2, 2024, 8:00 am PDT

register at: lnkd.in/g2NvDh-p
September 25, 2024 at 5:59 PM