Uploaded July 2026 | Updated November 2026, 11 hours ago
ADD THE DATA SCIENCE HANGOUT TO YOUR CALENDAR HERE: https://pos.it/dsh - All are welcome! We'd love to see you!
This week's guest was Will Landau, Senior Advisor of Innovative Statistics at Eli Lilly!
Some topics covered in this week's Hangout were building reproducible pipelines with the {targets} package, distributed and parallel computing with {crew} and {mirai}, designing trustworthy AI agents, choosing between Bayesian and frequentist approaches in clinical trials, and maintaining open source software in the age of AI.
One community member asked: When do you reach for a Bayesian approach over a frequentist one in a clinical trial, and how do you explain that choice to stakeholders?
Will's paraphrased answer: The familiar reason is prior information, whether you want to be opinionated about incorporating it through a rigorous prior or techniques like historical borrowing. But he's implemented plenty of Bayesian models on diffuse priors too, because they make early-phase decisions much easier to quantify. Rather than only asking whether a result is statistically significant, Bayesian models let you more conveniently answer the practical question: for example, the posterior probability of observing a large enough effect size, which is incredibly useful when deciding whether to move a therapy to a large Phase 3 registration study. You also don't need frequentist asymptotic approximations like the delta method, you can work directly with MCMC (markov chain monte carlo) and transformations on posterior samples.
Resources mentioned in the video and chat:
π targets Package bookβ books.ropensci.org/targets
π targets Package Documentation β docs.ropensci.org/targets
π targets on GitHub β github.com/ropensci/targets
π crew Package (distributed computing) β github.com/wlandau/crew
π mirai Package (async, parallel, and distributed computing) β mirai.r-lib.org
π Trusted Mini-Agents Guide (Will Landau) β wlandau.github.io/trusted-mini-agents
π RTMB Package β cran.r-project.org/web/packages/RTMB/index.html
π Will Landau's targets Workshop at R/Pharma 2023 β youtube.com/watch?v=cyF2dzloVLo&list=PLMtxz1fUYA5C0csy8-wTfFmRYQEB30vr3&index=12
π Will Landau & Charlie Gao joint talk at posit::conf(2025) β youtube.com/watch?v=s_cBi155ZIQ
π Data Science Lab episode with Charlie Gao on mirai β youtube.com/watch?v=Vf_jmY1tMWo&list=PL9HYL-VRX0oSeWeMEGQt0id7adYQXebhT&index=1
π "AI and the Invisible Newcomer in Open Source" by Mara Averick β blog.stdlib.io/ai-and-the-invisible-newcomer-in-open-source
π Kahn's Algorithm for Topological Sorting β medium.com/@robhernandez5/kahns-algorithm-for-topological-sorting-26f29f2eaf48
π XKCD: Dependency comic β xkcd.com/2347
π MLU-Explain (visual machine learning explanations) β mlu-explain.github.io
π Posit Academy β academy.posit.co
βΊ Subscribe to Our Channel Here: bit.ly/2TzgcOu
Follow Us Here:
Website: posit.co
Hangout: https://pos.it/dsh
The Lab: https://pos.it/dslab
LinkedIn: linkedin.com/company/posit-software
Bluesky: https://bsky.app/profile/posit.co
Thanks for hanging out with us! π
Timestamps:
00:00 Introduction
04:58 "Can you talk about the targets package?"
13:21 "You're doing great work to try to separate out that development support stuff from your day-to-day job and personal time and life. How the heck do you do it?"
16:57 "As someone who's primarily worked with tools like SnakeMake and Nextflow, why should I use targets, or what are some benefits of using targets over something like Nextflow?"
20:37 "How has Gen AI affected you as a package author and maintainer, mostly from other people submitting issues or PRs, and less about how you use it personally in your own work?"
25:06 "Do you want to talk a little bit about integrating Mirai to do things even faster?"
29:10 "How do you communicate uncertainty to people who want a single number?"
31:24 "What does an average day or week look like for you? How is your time divided between development, consulting, etcetera?"
34:00 "Have you had feedback from people using targets for agentic LLM workflows, for testing parameterization changes of RAG ingestion and associated changes to how the LLM instructions are dealing with that, or just anything in that creating and testing agentic workflows space?"
37:15 "When do you reach for a Bayesian approach over a frequentist one in a clinical trial, and how do you explain that choice to stakeholders?"
41:32 "Which Bayesian MCMC tool do you use? Do you use Stan, or the macros to get to Stan?"
45:56 "Is there a piece of career advice that you wish you knew before you started in data science, or anything that you think would be helpful for everybody else here?"
ADD THE DATA SCIENCE HANGOUT TO YOUR CALENDAR HERE: https://pos.it/dsh - All are welcome! We'd love to see you!
This week's guest was Will Landau, Senior Advisor of Innovative Statistics at Eli Lilly!
Some topics covered in this week's Hangout were building reproducible pipelines with the {targets} package, distributed and parallel computing with {crew} and {mirai}, designing trustworthy AI agents, choosing between Bayesian and frequentist approaches in clinical trials, and maintaining open source software in the age of AI.
One community member asked: When do you reach for a Bayesian approach over a frequentist one in a clinical trial, and how do you explain that choice to stakeholders?
Will's paraphrased answer: The familiar reason is prior information, whether you want to be opinionated about incorporating it through a rigorous prior or techniques like historical borrowing. But he's implemented plenty of Bayesian models on diffuse priors too, because they make early-phase decisions much easier to quantify. Rather than only asking whether a result is statistically significant, Bayesian models let you more conveniently answer the practical question: for example, the posterior probability of observing a large enough effect size, which is incredibly useful when deciding whether to move a therapy to a large Phase 3 registration study. You also don't need frequentist asymptotic approximations like the delta method, you can work directly with MCMC (markov chain monte carlo) and transformations on posterior samples.
Resources mentioned in the video and chat:
π targets Package bookβ books.ropensci.org/targets
π targets Package Documentation β docs.ropensci.org/targets
π targets on GitHub β github.com/ropensci/targets
π crew Package (distributed computing) β github.com/wlandau/crew
π mirai Package (async, parallel, and distributed computing) β mirai.r-lib.org
π Trusted Mini-Agents Guide (Will Landau) β wlandau.github.io/trusted-mini-agents
π RTMB Package β cran.r-project.org/web/packages/RTMB/index.html
π Will Landau's targets Workshop at R/Pharma 2023 β youtube.com/watch?v=cyF2dzloVLo&list=PLMtxz1fUYA5C0csy8-wTfFmRYQEB30vr3&index=12
π Will Landau & Charlie Gao joint talk at posit::conf(2025) β youtube.com/watch?v=s_cBi155ZIQ
π Data Science Lab episode with Charlie Gao on mirai β youtube.com/watch?v=Vf_jmY1tMWo&list=PL9HYL-VRX0oSeWeMEGQt0id7adYQXebhT&index=1
π "AI and the Invisible Newcomer in Open Source" by Mara Averick β blog.stdlib.io/ai-and-the-invisible-newcomer-in-open-source
π Kahn's Algorithm for Topological Sorting β medium.com/@robhernandez5/kahns-algorithm-for-topological-sorting-26f29f2eaf48
π XKCD: Dependency comic β xkcd.com/2347
π MLU-Explain (visual machine learning explanations) β mlu-explain.github.io
π Posit Academy β academy.posit.co
βΊ Subscribe to Our Channel Here: bit.ly/2TzgcOu
Follow Us Here:
Website: posit.co
Hangout: https://pos.it/dsh
The Lab: https://pos.it/dslab
LinkedIn: linkedin.com/company/posit-software
Bluesky: https://bsky.app/profile/posit.co
Thanks for hanging out with us! π
Timestamps:
00:00 Introduction
04:58 "Can you talk about the targets package?"
13:21 "You're doing great work to try to separate out that development support stuff from your day-to-day job and personal time and life. How the heck do you do it?"
16:57 "As someone who's primarily worked with tools like SnakeMake and Nextflow, why should I use targets, or what are some benefits of using targets over something like Nextflow?"
20:37 "How has Gen AI affected you as a package author and maintainer, mostly from other people submitting issues or PRs, and less about how you use it personally in your own work?"
25:06 "Do you want to talk a little bit about integrating Mirai to do things even faster?"
29:10 "How do you communicate uncertainty to people who want a single number?"
31:24 "What does an average day or week look like for you? How is your time divided between development, consulting, etcetera?"
34:00 "Have you had feedback from people using targets for agentic LLM workflows, for testing parameterization changes of RAG ingestion and associated changes to how the LLM instructions are dealing with that, or just anything in that creating and testing agentic workflows space?"
37:15 "When do you reach for a Bayesian approach over a frequentist one in a clinical trial, and how do you explain that choice to stakeholders?"
41:32 "Which Bayesian MCMC tool do you use? Do you use Stan, or the macros to get to Stan?"
45:56 "Is there a piece of career advice that you wish you knew before you started in data science, or anything that you think would be helpful for everybody else here?"
![Fun data science side projects | Damie Pak, Mark Rieke, & Sam Parmar | Data Science Lab
The Data Science Lab is a live weekly call. Register at pos.it/dslab! Discord invites go out each week on lives calls. Wed love to have you!
The Lab is an open, messy space for learning and asking questions. Think of it like pair coding with a friend or two. Learn something new, and share what you know to help others grow.
On this call, Libby Heeren is joined by Damie Pak, Mark Rieke, and Sam Parmar in a special community project showcase where three data scientists share their creative side projects.
Damie walks through her Mambo No. 5 Bayesian analysis project, showing how she used baby name data to predict when the song was released based on the womens names in the lyrics. Mark presents his Bayesian model analyzing player skill in Dropout TVs Um, Actually game show, revealing who truly is the best contestant when accounting for factors beyond simple win counts. Sam demonstrates his impressive collection of Quarto extensions (so prolific!!), including flashcards, quizzes, Easter eggs, and voice-controlled slides (yes, really). All three showcase the importance of working out loud, making mistakes publicly, and building silly projects to learn new skills.
Hosting crew from Posit: Libby Heeren, Isabella Velasquez
Damie Paks GitHub: https://github.com/pakdamie
Damie Paks Bluesky: https://bsky.app/profile/damiepak.bsky.social
Damie Paks LinkedIn: https://www.linkedin.com/in/damie-pak/
Mark Riekes GitHub: https://github.com/markjrieke
Mark Riekes Bluesky: https://bsky.app/profile/markjrieke.bsky.social
Mark Riekes LinkedIn: https://www.linkedin.com/in/markjrieke/
Sam Parmars GitHub: https://github.com/parmsam
Sam Parmars LinkedIn: https://www.linkedin.com/in/sam-parmar-/
Resources mentioned in the video and chat:
π Mambo No. 5 Bayesian Analysis (Damies project): https://yawpr.substack.com/p/project-a-little-bit-of-reverend
π Um, Actually Player Skill Analysis (Marks project): https://www.thedatadiary.net/posts/2024-10-06-actually/
π Statistical Rethinking book by Richard McElreath: https://xcelab.net/rm/
π Quarto Extensions Listing: https://quarto.org/docs/extensions/
π Mickaels Quarto Extensions Registry: https://m.canouil.dev/quarto-wizard/getting-started/
π Quarto Wizard Extension (by Mickael Canouil): https://m.canouil.dev/quarto-wizard/getting-started/
π Sam Parmars Quarto Extensions: https://github.com/parmsam/
π Quarto Easter Eggs Extension: https://parmsam.github.io/quarto-easter-eggs/
π Quarto Flashcards Extension: https://github.com/parmsam/quarto-flashcards
π Quarto Quiz Extension: https://github.com/parmsam/quarto-quiz
π Marcos Huertas Discord-style Spoiler Tags Extension: https://github.com/astrowonk/spoiler_shortcode
π Marcos Huertas Bootstrap Tooltips Extension: https://github.com/astrowonk/quarto_tooltips
π Rich Iannones Posit::conf 2023 talk on Quarto Extensions: https://www.youtube.com/watch?v=EihuM4oyOvs
π Anki Flashcard app: https://apps.ankiweb.net/
βΊ Subscribe to Our Channel Here: https://bit.ly/2TzgcOu
Follow Us Here:
Website: https://www.posit.co
Hangout: https://pos.it/dsh
The Lab: https://pos.it/dslab
LinkedIn: https://www.linkedin.com/company/posit-software
Bluesky: https://bsky.app/profile/posit.co
Thanks for hanging out with us! π
Timestamps of Questions / Topics:
00:00 Introduction
00:22 Damie Pak Intro: Mambo No. 5 project philosophy
03:03 Demoing the mathematical model and Bayesian statistics
04:11 Walking through project functions and US Social Security name data
08:13 Live coding: Testing if the analysis script runs
13:34 Did you use Claude or any other tools to help you with this?
16:44 Mark Rieke Intro: Bayesian stats and Um, Actually
22:34 Demoing the Bayesian model for player skill
25:14 How do you figure out what points were awarded to in a team game?
27:38 Have you shared your analysis with the Dropout of Actually people?
30:34 Does that mean that if somebody of high skill is playing against other contestants of low skill that that win is discounted?
34:04 Comparing statistical vs. geometric models for golf putts
35:46 What do you think about doing something like this for Game changer?
37:17 Sam Parmar Intro: Quarto extension adventures
40:06 How did you learn about all these extensions?
40:34 Navigating the Quarto extensions gallery
41:42 Demoing the Quarto Wizard extension in Positron
43:32 Demoing the Easter Eggs extension
45:52 Demoing the Flashcards extension
48:35 Demoing the Quiz extension
50:24 Is there a way to make it [flashcards] three sided?
51:10 Demoing the Quarto Excalidraw extension
51:55 Demoing the Speech extension for voice-controlled slides
53:29 How do extensions even work? Fun data science side projects | Damie Pak, Mark Rieke, & Sam Parmar | Data Science Lab](https://i.ytimg.com/vi/tFBDWLZpJuA/mqdefault.jpg)









