Nominations for 2022 Stan Governing Body

Stan Governance
1

As announced in Elections for the next Stan Governing Body , we will use the Stan forums for nominations for the 2022 Stan Governing Body (SGB).

Please respond to this post to self-nominate for either a 1-year or 2-year term on SGB before the end of November. We encourage all nominees to briefly summarize their experiences with Stan and their goals for the SGB. Feel free to add links to any content you think is relevant. And if you know someone who you think would be a good fit for the SGB please let them know and encourage them to nominate themselves.

For other details about the election and links to information about the SGB see Elections for the next Stan Governing Body . For examples of past nominations, here is last year’s thread.

–
Yi Zhang on behalf of @SGB

4 Likes
5

Dear Stan community,

I’m Jose Storopoli, and I’d like to nominate myself for SGB for a 1-yr term. I have started learning Bayesian statistics with Gelman’s et al. BDA 2013 book which led me to Stan.

My background

I am an Assistant Professor and Researcher of the Department of Computer Science at Universidade Nove de Julho - UNINOVE located in SĂŁo Paulo - Brazil.

I teach undergraduate and graduate courses in Data Science, Statistics, Bayesian Statistics, Machine Learning and Deep Learning using several languages such as Stan, Julia , R and Python . I’ve contributed to Julia , R and Stan ecosystems. I can handle some basic and intermediate templated C++. I have also published packages in Julia , Rust , R , and Python (pip) official repositories/registries.

I conduct research, publish and advise PhD candidates on topics about Bayesian Statistical Modeling and Machine Learning applied to Decision Making. Also, I am the Principal Investigator of LabCidades - Smart City Research Lab at UNINOVE.

Experience

My main experience is mostly academic. Using Stan in peer-reviewed academic publications and teaching Bayesian Statistics in my courses (I still use mainly brms, since it is a mixed class of students with several backgrounds). For instance,

I am also a certified tidyverse RStudio instructor.

Intended Contribution and SGB Goals

I think that still Latin America and other countries of the Global South are underrepresented in both academia and technology, which also happens in the Stan community. I would focus my goals on diversifying the Stan community and helping popularizing and capilarize to Latin America and the other Global South countries.

But I expect that my role as a SGB member would also involve other topics, such as community, fundraising, integrating the developers with the userbase. I would gladly also volunteer to assist in those other topics.

Kind regards,
I am available for further questions and don’t hesitate to contact me,

Jose Storopoli

19 Likes
6

All,

I would like to nominate myself, Breck Baldwin, for a two year position with the SGB.

I was executive director of the SGB in 2019 which transitioned the SGB from an appointed body to an elected one among other things. On the positive side, I created the paid positions for Community Organizer and YouTube manager.

I also created the Technical Director role that was more of a mixed experience and I’ll take the blame for the negative side of that. I think I have recognized the issues that made it problematic. Essentially communications were poor, decision-making was opaque at times, and community members didn’t feel heard. Voting with clear epochs of discussion/decision-making goes a long way towards sorting these issues out.

I have also been somewhat successful in raising funds for the SGB, $100k as exec dir and later another ~$100k for Stan’s share in a joint proposal with PyMC3 and Arviz that has not yet arrived.

My motivation for running stems from my appreciation of Bayesian modeling and the fact that Stan is the best package for advancing the approach. I consider the problems we take on to be vital to science and uniquely suited to Stan’s strengths and vision.

As an SGB member I’d focus on a few things:

  • Fundraising. We are spending down the balance from a high of around $600k with a current balance of $300k. This doesn’t include the anticipated $100k from the Chan Zuckerberg Initiative. Operating expenses are $60-100k annually but I’d like to see more funded operations but that requires money. For fundraising I’d support:

    • Continued grants through NumFOCUS.
    • Look to other fundraising approaches, e.g,. a zero-benefit license that can be a line item for organizations that have an easier time buying things than donations. This is an idea that has been considered before.

  • Continue to pay for, and if possible increase funding for worthwhile things like:

    • Community organizers–I think this is more than one job, Martin did a great job, but I’d like to see more work supporting users/developers.
    • Software developers are always needed and paying them helps get things done that don’t appeal to volunteers.
    • Teaching/evangelizing opportunities like Aki’s Global South course should have financial support.

  • Establishing technical planning and leadership. The last effort in this direction was pretty rough but that doesn’t mean we should not try again.

  • Improving the usability of Stan is also a priority. This spans installation, documentation, teaching, and user support.

  • I think there is some governance debt that should be resolved. I’d like to get the electorate sorted out as well as making concrete how administrative roles are managed. I’d like to maximize transparency balanced by keeping personal issues/discussions private.

Happy to answer questions.

Thanks

Breck

12 Likes
7

it’s Nov 30th, and we clearly don’t have enough candidates.
could we extend the deadline through end of January?
(because the holidays are disruptive).

4 Likes
8

That sounds reasonable. Let’s extend the nomination to Jan 15 and hold the election afterwards so we can have a new SGB on Jan 31.

1 Like
9

Let’s also use this thread for Q&As. Feel free to interact with our candidates about their achievement, ambition, and future plans around Stan.

1 Like
10

I am wondering what the time commitment is? I like the idea of nominating myself :), but I also have to sink time into funding and job hunting on top of my current work load.

14 Likes
11

In the past year I’d say I spent ~2-6 hr/wk in addition to the weekly ~1hr meeting. It really depends on the how things progress and the agenda at the time. I usually spend the hours on reviewing discourse threads, contact interest parties, attend related meetings, and drafting documents. There’s also a seasonality as summers tend to be quiet. Let me know if you need more details. Thanks for considering!

10 Likes
12

Dear Stan community,

I’m Angie (Hyunji) Moon, and I would like to nominate myself for SGB for one year term.

I am a PhD student at Columbia University, working with Andrew Gelman and Garud Iyengar. My major is operations research. It has been more than four years since I fell in love with Stan and its community. Stan introduced me to inspiring tales of probability and computation, mentors with great minds, and lifelong friends which became a major part of my life. In the hope that more people can also experience this joy, I continuously took the initiative including the following:

  1. initiated StanKorea community and its youtube channel (750 subscriber)
  2. arranged several meetups and study groups
  3. translated BDA into Korean (published)
  4. shared research with reproducible codes as Stancon speaker 19, 20
  5. organized StanConnect Simulation-based calibration
  6. contributed to Stan as its developer

For SGB goals, I would like to encourage
i) active workshops and events
ii) smoother communication between developers and users
for warmer and satisfactory Stan experience.

Best regards and I am available for further questions,
Angie (Hyunji) Moon

15 Likes
13

Dear Community,

I am Caetano Souto Maior, and I would like to nominate myself for a two-year term in the Stan Governing Body.

I am currently a Postdoctoral Fellow in the Applied Statistics group at the Basque Center for Applied Mathematics (BCAM), where I am using Hamiltonian Monte Carlo (and improvements on its basic formulation) with nonlinear dynamic models.
My background, nevertheless, is in the natural sciences, where I have been not only defending but also applying bayesian inference for almost a decade.
I am faculty at the FAES Graduate School @ NIH teaching Linear Algebra with Applications in Statistics; Single; and Multivariate Calculus, as well as a certified trainer at The Carpentries. I have also volunteered as a translator for Raspberry Pi.

In that context, my intended contribution to the Stan Community is threefold:

  1. Help HMC algorithms to become more broadly understandable: Make education-oriented implementations of HMC, particularly with functional programming style that more closely encode the essential mathematical/statistical functions/descriptions of bayesian inference and MCMC.
    The expected result of this goal is to have simpler, more concise algorithms that allow the inner workings of MCMC to be easily explained to both newcomers and users of a broad range of backgrounds – also, the goal is to make more advanced features (like those implemented in Stan) to be less opaque;

  2. Expand the use of HMC in the natural sciences: Contribute to the dissemination of Hamiltonian Monte Carlo in process-oriented (often dynamic, nonlinear) modeling, with all of its constraints and specificities.
    The expected result is that researchers (biologists and life scientists especially) will become boradly aware of the power of bayesian inference and HMC; conversely, statisticians should be able to recognize the associated difficulties;

  3. Benchmarking: Build on goals 1 and 2 to implement different samplers applied to classical mechanistic models (like infectious disease dynamics with SIR-like models) as case studies oriented towards teaching/training.
    The expected result is a sort of benchmark for general sampler performance in more realistic models (e.g. Gradient-based vs. Metropolis-Hastings schemes), as well as for the computational cost of some features that make Stan user-friendly (e.g. auto-differentiation vs. analytical/numerical gradients, static vs. dynamic step numbers or intermediate approaches).

I also second proposals of some of the other nominees, especially the increased representation of the Global South – as a native Portuguese speaker living in a Spanish-speaking country I would be happy to contribute to efforts to translate any material to the two languages, spoken by around 800 million people worldwide. I am also eager to work with other members with different backgrounds and views, both to define priorities and improve efficiency of efforts, as well as to learn about other aspects of governing a successful project like Stan.

I am available to answer and questions or concerns, as well as to elaborate on the proposals summarized in points 1-3.

best,
Caetano

10 Likes
14

These sound like some great initiatives and ideas for the next SGB to tackle.

As a member of the SGB in 2018-2019 (I think we were always a provisional board), I have appreciated having new people on the board since then, and I think Stan benefits from this.

5 Likes
15

All,

I would like to nominate myself for a one-year term in the Stan Governing Body.

I am a Senior Director of Data Science at Bully Pulpit Interactive. I have worked in various analytic and data science roles for over a decade - starting in the insurance industry and transitioning to marketing analytics - where I’ve championed the use of Stan and a Bayesian workflow. I’m currently interested in using Stan for media measurement, election polling, and audience definition creation.

I am an active Stan community member and a Stan developer. Back in 2020 I started to contribute back to Stan because it has given me so much. Without prior C++ experience, I was welcomed into the developer realm, getting setup, understanding what I needed of the C++, and have contributed a few functions and ideas back into the language. In addition I maintain a helpful Stan functions repo meant to house user defined functions that can find wider use and have started a Stan cheatsheets site that admittedly needs a lot more love.

I am a passionate supporter of Stan because it is clear, documented, open-source, and has a vibrant community. The idea of Stan - the language, the community, and the documentation - is driven by a pedagogical imperative to enable researchers to think deeply about the complexities of their data. Stan’s flexibility encourages testing assumptions, incorporating real world complexities, and diagnosing model problems, without having to write completely custom samplers and methods from scratch. This is an era of the modeling equivalent to the Cambrian explosion of life, the complexity and diversification of models enabled by Stan is exploding. The hardest part now is often getting Stan installed ;).

As a board member I hope to continue to support the tradition of this welcoming community and getting models built that fit the needs of the data, rather than the other way around.

As a SGB member I would like to:

  • Establish a plan for more openness about technical planning, roadmaps, and priorities over the short-term (3 - 6 months) and longer term (1 - 5 years). We need to know where we want to go in order to have the resources to get there.
  • Add more corporate sponsors. There are the giant corporations that develop their own (possibly open-source) PPL, and then there are the hundreds of organizations which can’t. I would like to reach out to these and offer them clearly defined benefits for their sponsorship. That may include priority development of new functionality, developing case studies which target their problem areas, and overall promotion (such as this event is sponsored by “X a leading Y company”).
  • Conduct surveys on the community and wider. We need to understand the reasons that someone has decided to use or not use Stan. The current information we have comes from informal and limited samples across github issues, Twitter, and the forums. Not everyone is willing to speak up candidly. A formal survey can help answer questions like: What were the barriers to using Stan? What was good? What do they think can be improved? This information will be critical for developing priorities and future roadmap items.

Please reach out if you have any questions.

Best,

Sean Pinkney

18 Likes
16

Hello,

I would like to nominate myself for a two-year term in the Stan Governing Body.

I’ve been a Stan contributor since 2014. My main contributions have been as a Stan developer, most recently, developing CmdStanPy. In 2017 I jumped into the deep end of the Bayesian Modeling pond by working with folks at NYU to implement a popular disease mapping model the BYM2 model in Stan, with lots of help from Dan Simpson and Andrew Gelman. Since then I’ve continued to write about and give talks on this model and Stan modeling in general at conferences and meetups, including StanCon (of course), PyData, and WiMLDS meetups. It’s very satisfying to work on the Stan project and interact with so many different kinds of people working on so many different kinds of applications.

The Stan project continues to mature. I think that the two previous elected SGB’s have put in place a good set of policies and procedures, notably the developer voting procedure and the code of conduct and adjudication committee. Most importantly, they managed to keep StanCon going throughout the ongoing COVID pandemic, starting with the online global StanCon in 2020 and the StanCon Connect sessions in 2021.

As a member of the SGB, I would advocate:

  • Creating more events and resources for Stan education and outreach.

  • Drawing up guidelines for fund-raising and fund-giving as well as providing more transparency around the Stan NumFOCUS funding and expenditures.

  • Streamlining SGB processes in order to reduce the time commitment required of its members.

  • Working with the Stan developers to make sure that the Stan software eco-system continues to improve and that the developer community is open as well as open-source.

Now that the previous boards have established a working framework for governance, the focus of the SGB should shift towards education and outreach. We should continue to sponsor StanCon connect sessions and other kinds of conferences, tutorials, and workshops. We should encourage Stan users to self-organize along many dimensions and to create more specialized field guides like the current “Stan for X” repositories https://cognitive-science-stan.github.io, https://education-stan.github.io., https://stanecology.github.io, and https://epidemiology-stan.github.io.

A secondary focus is overall project sustainability. We need to make the serving on the SGB be a far more lightweight time commitment than it is currently, so that more and different people will be able to participate.

A large part of the reason for being a part of NumFOCUS is to help on the funding front. In the past year I’ve helped raise $650K for Andrew Gelman at Columbia. I would be happy to work with the SGB, NumFOCUS, and the community at large to raise funds through the Stan NumFOCUS non-profit in order to realize that above goals.

These are my qualifications and agenda. Questions welcome!

cheers,
Mitzi

18 Likes
17

Dear Stan Community,

I am Vianey Leos Barajas and would like to nominate myself for a two-year term in the Stan Governing Body.

I am an assistant professor at the University of Toronto, in the Department of Statistical Sciences and the School of the Environment. I am currently teaching a graduate level course in ecological statistics that uses Stan for Bayesian inference and am the creator of the stanecology page – which led to the creation of a few other domain-specific pages as well. I use Stan for research, as do my students.

As a member of the SGB, I would like to advocate for:

  1. A focus on domain-specific outreach and creation of materials that encourages users to use Stan. For instance, encouraging StanConnect events and discussing how to make the domain-specific pages the best they can be to serve different communities.
  2. Make concrete plans for the inclusion of women and other systemically excluded groups not represented in the Stan community. The group is not very diverse – there need to be internal discussions as well to understand what factors have played a role in this.
  3. Dissemination of Bayesian statistics and Stan throughout Latin America by participating in events such as LatinR.

As a woman of color, I have felt welcomed in the Stan community but there’s a clear lack of diversity. Unless an effort is made by the Stan core, I do not think this will change anytime soon.

Vianey

13 Likes
18

Hi all,

Voting is currently underway. It is worth noting that Angie (Hyunji) Moon decided to opt off from the list of candidates and is therefore not on the ballot.

Kind regards, Duco

2 Likes
19

Is there a link to the voting?

20

I got email with the link