After nearly 8 years using Stan, and 20 years in my field, I will be leaving my current role and moving to a different domain.
What Stan gave me goes well beyond building models: it fundamentally changed how I understand data and their generative processes. Modeling became the visible layer of a deeper, principled Bayesian workflow that shaped my professional thinking.
I am grateful to this community: consistently rigorous, welcoming, and never inclined to oversimplify. The guidance I received always pushed me toward better questions and deeper understanding.
I tried to give something back by sharing code and workflows, hoping they could serve as a starting point for others facing similar challenges.
If I have one regret, it is not having fully bridged what I was doing with INLA (for computational speed) into Stan (for modeling flexibility). This is only a personal limitation. Recent work on approximate inference in Stan highlights the strength and evolution of the ecosystem.
Still, I leave with a strong sense of gratitude: Stan, and its community, have helped me maintain a high professional standard and, more broadly, have changed the way I think… and the way I see the world.
Thanks so much for letting us know! This is one of the really nice things about working on open source—people are genuinely grateful. For me, it was really a two-way street. I used answering questions on the forums in the first couple years of the project as a way to prioritize which bits of statistics I learned.
I also feel very lucky that our community is so constructive. It’s what I always cite as the main factor in the project’s success (the other two big factors I cite are the marketing reach of @andrewgelman and starting with three devs with industry experience). When we were first building Stan, I barely understood applied stats or C++. I couldn’t have asked for a better set of mentors than the early Stan dev team, @andrewgelman, @matthewdhoffman, @syclik, @bgoodri, and @betanalpha, all of whom still know a lot more about stats than me!