Tigers need your help.

Jim Logue, Director of Baseball R&D at the Detroit Tigers, writes:

We are now hiring a Principal Quantitative Analyst. With this position we’re looking for someone with extensive Bayesian experience, with a secondary emphasis on baseball knowledge.

The Tigers went 66-96 last year so the good news is that if you join them now you can take some credit for whatever improvement they show next year!

I assume that knowledge of Stan will be a plus.

A baseball analytics job using Stan!

Tony Williams writes:

I have nothing to do with this job, but it might be interesting to your readers since they specifically mention Stan as a desired skill.

From the link:

Data Scientist, Baseball Research & Development

The Cleveland Guardians Baseball Research & Development (R&D) group is seeking data scientists at a variety of experience levels . . . You will analyze video, player tracking, and biomechanics data as well as traditional baseball data sources like box scores to help us acquire and develop baseball players into a championship-caliber team. . . .

Qualifications

– Demonstrated experience or advanced degree in a quantitative field such as Statistics, Computer Science, Economics, Machine Learning, or Operations Research.

– Programming skills in a language such as R or Python to work efficiently at scale with large data sets.

– Desire to continue learning about data science applications in baseball.

And then in the Preferred Experience section, along with “Demonstrated research experience in a sports context (baseball is a plus)” and “Experience with computer vision” and a few other things, they have:

– Experience with Bayesian statistics and languages such as Stan.

How cool is that??

And, hey! I just looked it up . . . the Guardians have a winning record this year and they’re headed for the playoffs! Nothing like the Cleveland MLB teams I remember from my childhood . . .

Calling all epidemiology-ish methodology-ish folks!

I just wanted to share that my department, Epidemiology at the University of Michigan School of Public Health, has just opened up a search for a tenure-track Assistant Professor position.

We are looking in particular for folks who are pushing forward innovative epidemiological methodology, from causal inference and infectious disease transmission modeling to the ever-expanding world of “-omics”.

We’ll be reviewing applications starting October 12th; don’t hesitate to reach out to me ([email protected]) or the search committee ([email protected]) if you have any questions!

Also – you can find the posting here.

Programmer position with our research group—at the University of Michigan!

Hey, midwesterners—here’s a chance for you to join the big team! It’s for our research project with Yajuan Si, Len Covello, Mitzi Morris, Jonah Gabry, and others on building models and software for epidemic tracking (see this paper, this paper, or, for the short version, this op-ed):

Summary

The Survey Research Center (SRC) at the University of Michigan’s Institute for Social Research (ISR) invites applications for a Full Stack Programmer with the Survey Methodology Program, in collaboration with the team of Stan developers at Columbia University.

Our multidisciplinary research team is involved in cutting-edge statistical methodology research and the development of computational algorithms, software, and web-based interfaces for application and visualization. We are looking for a Full-Stack Programmer to work on an innovative infrastructure to enable user-friendly implementation and reproducibility of statistical methods for population generalizability. The position provides an opportunity to work in an exciting and rewarding research area that constantly poses new technical and computational problems.

Responsibilities*

Develop, test, maintain, document, and deploy an interface for statistical inferences with sample data and result visualization, specifically the implementation of multilevel regression and poststratification.

Provide timely technical support during research deployments.
Create documentation and tutorials about the developed applications for use by interdisciplinary research teams.

Required Qualifications*

Bachelor’s or Master’s degree in Statistics/Computer Science/Information Science/Informatics or related technical discipline or a combination of education and software-development experience in a research or corporate environment to equal three (3) years.

Skills in R/Python programming.

Experience in data visualization and dashboard construction.

Experience with databases. Direct experience with demographic or geospatial data a plus.

Familiarity with C++ or Java. Knowledge with Stan programming a plus.

Track record of successful application development a plus.

Desired Qualifications*

Dashboard development experience preferred.

Work Locations

This position will be on-site at the University of Michigan offices in Ann Arbor, with flexible scheduling and remote opportunities made available within our overall Center policies. If relocation is required, we will allow for reasonable time and flexibility to make necessary arrangements.

This is an exciting research project and we’re hoping to find someone who can take a lead on the programming. Click through to the link for more details and to apply.

Job opportunity for a Stan user at Dugway

Scott Hunter writes:

Job opportunity as a statistician at US Army Dugway Proving Ground, in remote Dugway, Utah. Work is rewarding in that we solve problems to improve protecting our warfighters from chemical and biological attacks. Looking for someone comfortable coding in R and Stan (primarily using the rstan and rstanarm packages). Most problems deal with linear models as well as logistic models which may or may not be hierarchical. Design of Experiment experience is a plus as well as writing Shiny applications. Pay will depend on education/experience and ranges from $66,214 to $122,684 (GS11 – GS13 pay scale). Work week is Monday through Thursday with telework opportunities. If there is any interest, please send a resume soonest to [email protected].

I’ve done some Stan trainings for this group in the past and I really enjoyed working with them!

A professional writing coach gets GPT-3 to write an entire five-paragraph essay, complete with fake references!

It’s a careful process, as Basbøll explains:

For those who are playing along at home (i.e., those who have their own OpenAI account), you can access my presets here. (Model: text-davinci-002; Temperature: .77; Maximum length: 208; Top P: .9; Frequency penalty: .95; Presence penalty: .95; Best of: 18. . . .

My approach is to, first, prompt the model with a title and a key sentence, and from there with the edited result and a new key sentences in five or six iterations, until I have a five-paragraph essay. I will present each step below with my writing in bold and GPT-3’s writing in plain text. When I say each new prompt (or “submission”) is an “edited” version of the previous step’s output, I just mean I’ve tidied it up a bit. Usually removing line breaks to produce a visually neat paragraph. . . . GPT-3 actually catches on to this and begins to structure its new output to match my guidelines.

The details are at the linked post. Below are the inputs Basbøll used, in order. He did not present them all at once. He gradually introduced them in producing the essay.

The Significance of Sleep

Matthew Walker is a prominent sleep researcher.

(2017) [inserted to encourage GPT-3 to use APA-style referencing]

Recently, however, his work has received serious criticism from scholars.

Walker continues to make bold claims about the importance of sleep in the media.

Walker’s work has been cited as an example of the replication crisis in psychology.

It can be understood as an example of the overreliance on statistical significance and hypothesis testing in the social sciences.

In conclusion,

This does not mean that Walker’s work is completely false. It does, however, raise some concerns about his research practices. Future studies and criticism will

References

Walker, M.

References

Basbøll writes, “Here’s the text as it appears in the final version. It consists of 1024 tokens. The bolded text is my contribution. The rest is GPT-3”:

The Significance of Sleep

Matthew Walker is a prominent sleep researcher. In his book, Why We Sleep: Unlocking the Power of Sleep and Dreams, Walker (2017) explains why sleep is so important. Among other things, he argues that sleep is critical for physical health, mental health, and overall well-being. Walker argues that sleep is essential for physical health. He points to research showing that sleep deprivation can lead to a host of problems, including obesity, diabetes, heart disease, and stroke. He also notes that sleep is important for immunity and healing. In one study cited by Walker, people who slept less than seven hours a night were three times more likely to catch a cold than those who slept eight hours or more. Walker also argues that sleep is essential for mental health. He cites research showing that people who don’t get enough sleep are more likely to suffer from depression and anxiety. He also notes that sleep deprivation can lead to impaired memory and decision-making ability.

Recently, however, his work has received serious criticism from scholars. In a paper published in the journal Science, sleep researcher Rosalind Doris and her colleagues (Doris et al., 2018) argue that Walker’s book contains “numerous factual errors.” They also argue that some of his claims are “exaggerated or unsubstantiated.” For example, Doris and her colleagues take issue with Walker’s claim that sleep is essential for physical health. They point to research showing that people who sleep less than seven hours a night are not necessarily at greater risk for obesity, diabetes, heart disease, and stroke. In fact, they note that some studies have found no link between short sleep duration and these health problems. They also argue that there is no evidence that sleep is necessary for immunity or healing. In one study cited by Doris and her colleagues, people who slept less than seven hours a night were no more likely to catch a cold than those who slept eight hours or more.

Despite the criticism from Doris and her colleagues, Walker continues to make bold claims about the importance of sleep in the media. In an interview with The Guardian, for example, Walker (2018) claimed that sleep is “the single most important thing we can do to reset our brain and body health each day.” He also claimed that sleep deprivation is a “public health epidemic.”

Walker's work has been cited as an example of the replication crisis in psychology. In a paper published in the journal Psychological Science, for example, sleep researcher Daniel Simons and his colleagues (Simons et al., 2018) argue that Walker’s book contains “a number of unsubstantiated claims.” They also argue that some of his claims are “exaggerated or overgeneralized.” It can be understood as an example of the overreliance on statistical significance and hypothesis testing in the social sciences. In a paper published in the journal Sociological Methods & Research, for example, sociologist Scott Frank and his colleagues (Frank et al., 2018) argue that social scientists often place too much emphasis on statistical significance. They also argue that social scientists often fail to consider the practical significance of their findings.

This does not mean that Walker's work is completely false. It does, however, raise some concerns about his research practices. Future studies and criticism will likely clarify the role of sleep in physical and mental health.

References

Doris, R. M., et al. (2018). Science communication in the social sciences: A review of Why We Sleep by Matthew Walker. Science, 361(6398), eaao5447. https://doi.org/10.1126/science.aao5447

Frank, S., et al. (2018). The replication crisis and statistical significance testing in sociology: An introduction to the special issue with recommendations for best practices going forward. Sociological Methods & Research, 47(2), 305-327. https://doi.org/10/1177%2F0049124116676024

Simons, D., et al. (2018). Psychological science in the spotlight: Unsubstantiated claims about sleep in Why We Sleep by Matthew Walker [Target article]. Psychological Science, 29(1), 15-19. https://doi-org./10/1177%2F0956797617741337

Walker, M. (2017). Why we sleep: Unlocking the power of sleep and dreams. New York, NY: Scribner.

Walker, M. (2018, February 2). ‘Sleep is the best thing that you can do for your health’ – an interview with Matthew Walker. The Guardian. Retrieved from https://www.theguardian.com/lifeandstyle/2018/feb/02/sleep-best-thing-you-can-do-for-your-health

This is absolutely hilarious, all the way down to the made-up but somehow convincing references by R. M. Doris, D. Simons, etc. There’s also a fun little follow-up dialogue which you can find near the end of the linked post.

Basbøll concludes:

The experiment cost about 4.00 USD.

All in all, GPT-3 seems to be able to produce very plausible prose. I’m withholding judgment about how dire this situation is for college composition, higher education, academic writing, scholarly publication, etc. until I think some more about it, and do some more experiments. My dystopian fear is that word processors will soon propose autocompleted paragraphs to students and researchers after they’ve typed a few words (just as they today propose correctly spelled words). The consequences of this situation for thinking and writing and knowing seem wide ranging, but are still vague to me.

I agree that auto-complete for paragraphs sounds like a real possibility, and the striking thing here is now similar the above essay looks to something like a real student would write, or something that might be published in a real social science journal. Who would think of checking the details of these references, etc., if they didn’t know to check? GPT-3 (with some help from Basbøll) might win a Turing test if pitted against the Cornell Food and Brand Lab.

I also appreciate the direct openness of Basbøll’s description of his experiment, which is much better than when that Google dude hyped his chatbot without sharing any details, documentation, etc.

However, as with any AI system, there are also potential risks and limitations associated with ChatGPT. For example, the model may sometimes generate essays or inaccurate responses, particularly when it is exposed to biased or incomplete data. Additionally, there is a risk that the model may be used to spread misinformation or disinformation, particularly in the context of social media and online communities.

Also, recall that Basbøll is a professional writing coach, which perhaps explains in part how he was able to put in so little input and coach GPT-3 to writing such a plausible (yet horrifying) essay. That’s a skill of a writing coach: to stimulate good work using a minimum of input. Perhaps the ability of doing this for a chatbot is similar to the ability of doing this for a student.

Fun July 4th statistics story! Too many melons, not enough dogs.

Just in time before the holiday ends . . . A correspondent who wishes to remain anonymous points us to this:

Apparently this was written by our former ambassador to the United Nations. I googled and her bachelor’s degree was in accounting! They teach you how to take averages in accounting school, don’t they?? So I’m guessing this particular post was written by someone less well-educated, maybe a staffer with a political science degree or something like that.

But what really gets me is, who eats only 1 hot dog on July 4th? No burger, no chicken, just one hot dog?? Is this staffer on a diet, or what?? Also, get it going, dude! Throw in a burger and some chicken breasts and you can get that inflation rate over 100%, no?

Meanwhile this person’s eating an entire watermelon? The wiener/watermelon ratio at this BBQ is totally wack. I just hope these staffers are more careful with their fireworks tonight than they were with their shopping earlier today. What’re they gonna do with all those extra watermelons?

Academic jobs in Bayesian workflow and decision making

This job post (with two reserach topics) is by Aki (I promise that next time I post about something else)

I’m looking for postdocs and doctoral students to work with me on Bayesian workflow at Aalto University, Finland. You can apply through a joint call (with many more other related topics) application forms for postdocs) and for doctoral students.

We’re also looking for postdocs and doctoral students to work on Probabilistic modeling for assisting human decision making in with Finnish Center for Artificial Intelligence funding. You can apply through a joint call (with many more probabilistic modeling topics) application form.

To get some idea on how we might approach these topics, you can check what I’ve been recently talking and working.

For five years straight, starting in 2018, the World Happiness Report has singled out Finland as the happiest country on the planet

Postdoc opportunity in San Francisco: methods research in public health

Angela Aidala points us to this ad:

Evidence for Action (E4A) is hiring a postdoc to work in our Methods Lab to help develop and share approaches to overcoming methodological challenges in research to advance health and racial equity. The postdoc should have training and interest in quantitative research methods and their application toward dismantling root causes of health inequities.

The individual will work on emerging topics that may focus on areas such as critical perspectives on quantitative methods in disparities research, data pooling to address small sample sizes, and development of measures relevant to advancing racial equity.

For full consideration, applications are due June 27, 2022. For more information visit https://e4action.org/PostDoc

They say:

The methods issues that arise in research on social conditions and health can be particularly difficult: pure randomization is rarely feasible, measurement is challenging, and causal pathways underlying effects are complex and cyclical.

Yup. They don’t explicitly mention Bayes/Stan, but it couldn’ thurt.

Applied statistics job at Leeds University, research in weather and climate change in partnership with the U.K. Meteorological Office

Colin Goodall writes:

I was asked by Robert Akroyd, Statistics Department Head at Leeds University in the UK, to forward “>this announcement of an opening jointly between Statistics and the UK Met Office.

The position may be of considerable interest and value to a data scientist/statistician seeking a strong subject matter background in weather and climate change. I wish I were earlier on in my career!

The deadline for a simple application is fairly soon, May 31.

And here it is:

Lecturer or Associate Professor in Applied Statistics, Leeds, UK

We invite applications from outstanding individuals in the areas of Statistics, Applied Probability and Data Science/Analytics to join us in the Department of Statistics, University of Leeds, UK. We encourage applicants of different genders and ethnicity.

Lecturer or Associate Professor in Applied Statistics (Grade 8 to Grade 9)

We are seeking a talented researcher to join our School of Mathematics. This unique role is part of a strategic investment by the University in the areas of statistics and data science. Further, specifically this post builds on the existing Met Office Academic Partnership (MOAP) at Leeds, led from the School of Earth and Environment, to provide new links between the Met Office and the School of Mathematics. This is an excellent opportunity to deliver high impact real world scientific research that will enhance the Met Office’s capability, improve the quality of their products and predictions and improve advice to all Met Office customers. You will have an excellent research record with the ability to collaborate effectively in a multidisciplinary setting, an aspiration to obtain external research funding and a passion for delivering first-class inspirational teaching and supervision within a research-intensive university.

We are happy to discuss the post informally. To explore the post further, or for any queries, please contact:

Robert Aykroyd, Head of Statistics, Department of Statistics
Email: [email protected]

Kurt Langfeld, Head of School, School of Mathematics
Email: [email protected]

Warner Music Group wants to hire Bayesians!

For reals!

They’re hiring an Operations Research Optimization Scientist and a Vice President Data Science, who will:

• Instantiate & Productionize a suite of enterprise level models and applications that service the global WMG business. In particular: data pipelines, production-ready models for forecasting, API interfaces for UI/UX
• Lead expertise in productionization of a Bayesian predicting suite and in Bayesian model workflow.
• Hands-on assist with business facing imperatives: ad hoc research requests, statistical models and knowledge
reporting.

See here for further background. I can’t confirm that if you take this job you’ll get to meet the members of Nickelback, but I can’t confirm that this won’t happen either.

Postdoc and research software engineer positions at Aalto University, Finland

This job ad is by Aki

I (Aki) have 1-2 postdoc positions open in my group for developing Bayesian inference methods, diagnostics, computation, workflow, probabilistic programming tools, teaching Bayesian data analysis, etc. If you’ve been following this blog, you probably know what kind of things I and Andrew work on. You can also check some of my talks and my recent publications. The specific tasks will be agreed based on the background, interests and future goals. Aalto University and nearby University of Helsinki has a big and active Bayesian and machine learning community, Finland has been ranked several times as the happiest country in the world, and Helsinki is among the most liveable cities. We collaborate actively with Stan, ArviZ and PyMC developers so the methods developed will have wide impact. There is no deadline for application nor official call page (we have those also twice per year) for these positions. You can find my contact information from my web page. Knowledge of Bayesian methods is a must, and experience in free software is a big plus. The length of the contract can be 1-2 years with option for extension.

Aalto University has also open a permanent position for a research software engineer. Aalto Scientific Computing is an elite “special forces” unit of Research IT, providing high-performance computing hardware, management, research support, teaching, and training. The team consists of a core of PhD staff working with top researchers throughout the university. All the work is open-source by default, and they take an active part in worldwide projects. They are looking for both people 1) with PhD degree with research experience in some computational field, and 2) software developer or computational scientist with a strong software/open source/Linux background, scientific computing experience, and some experience in research, with Masters degree or similar experience. This particular call emphasizes the ability to work in machine learning and AI environments. The ideal candidate will be working closely with machine learning researchers, and thus a background in machine learning is highly desirable. They are counting Bayesian probabilistic programming also as part of machine learning, so you could end up helping also my group. See more information and how to apply.

PhD student position in Stuttgart . . . to work on Stan! Latent variable models in psychology and the social sciences. With Paul “brms” Buerkner!

Paul Buerkner writes:

A lot of concepts in psychology and the social sciences can be formulated in terms of latent variables measured indirectly by observable data. However, existing statistical approaches remain limited in how they can express latent variables and relate them to each other. The goal of this project is to build advanced statistical models that better respect the probabilistic structures of latent variables and thus allow to obtain improved insights and predictions based on such variables. The primary goal of the proposed research is to develop a framework for Bayesian distributional latent variable models (BD-LVMs) that combines the principles of IRT and SEM with the flexibility of distributional regression powered by modern Bayesian estimation methods. Throughout the project, we will make extensive use of Stan and will later on integrate the developed methods in brms as well.

For more details about the position, please see https://www.stellenwerk.de/stuttgart/jobboerse/phd-student-position-mfd-part-time-75prozent-payment-according-to-e13-tv-l-temporary-for-the-duration-of-3-years-220304-82653/

Looks like fun!

Warner Music Group wants to hire a Stan programmer as VP Audience Data Science!

OK, I was kidding about the “Stan programmer” thing. But not really kidding. According to the job announcement:

The Data Science department works to influence WMG’s strategy and optimize immediate and long-term operations through data and insights. . . . This person in this role will be WMG’s expert in data science for Audience, will help create a deep institutional understanding for how our fan segments interact with and explore our music. The person in this role will:

• Help to establish best practices for curating and encouraging resonant consumption of WMG’s catalog repertoire & breaking hits;

• Gauge the impact of marketing initiatives and campaigns upon audience segments; be the subject matter guide to understanding listener behavior;

• Shape music content creation and delivery from a nuanced and sophisticated understanding of how, where, and when people listen to music given modern delivery and consumption of media.

They list proficiency in Stan as one of the attributes they’re looking for. In all seriousness, being able to fit serious Bayesian models in Stan should be helpful to attack the problems they’re working on at Warner Music Group.

Also, you’ll report to the Senior Vice President of Data Science—that’s Kobi! Kobi’s a serious dude, I’m sure he’d be a great boss.

P.S. I did some wikipedia surfing and it seems that Warner Music Group handles R.E.M., and Nickelback too! So you really can’t go wrong there.

How do things work at top econ journals, exactly? This is one weird-ass story:

Someone pointed me to this webpage with a hilarious story of a dispute among academic economists.

The author is Kenneth Judd, and here’s his summary of what happened:

The documents below detail the battle I [Judd] had with JPE [Journal of Political Economy] regarding a paper I wrote and submitted to JPE in November, 2012.

Here is the short version:

1. JPE rejected the paper because we did uncertainty quantification, also known as sensitivity analysis.

2. I contacted Jim Heckman regarding this decision, and he told us to change the title, resubmit the paper and that he would handle the new submission.

3. Heckman said that he would reject the paper if — in public comments and not in the paper — I criticized the JPE editor for the hostility to uncertainty quantification.

4. I obeyed Heckman’s gag order while we worked on the revision. However, when we sent the revision to JPE I took my name off the paper.

5. I contacted the University of Chicago asking if Heckman’s threats violated their standards for freedom of speech. The answer from UC was emphatic approval of Heckman’s threats.

6. The paper came out in JPE in December, 2019.

In 2020, I asked JPE if I could publicly display the correspondence regarding this matter. They agreed. I post the documents below.
The emails below show that many people at UC were aware of this conflict. No one expressed any criticism of how JPE treated this paper. While my comments focus on my emails with Heckman, it is clear that all the people who knew about this fully supported Heckman in his threats. Heckman was merely the chief spokesman of a gang of UC professors and administrators who believe that it is appropriate for a journal editor to use his editorial power to silence those who want to criticize standard economic methodology.

The good news is that none of this happened in a parking lot, and it seems that nobody got hurt.

Whether Heckman’s email statements should be characterized as “threats” and whether they violate the University of Chicago’s standards for freedom of speech . . . I’ll let you make the call.

Here’s the relevant bit from Heckman:

So, yeah, he’s saying, Shut up about this or we won’t publish your article. In case that wasn’t clear enough, Heckman reiterated a couple days later:

I can see two arguments that this does not violate the university’s free speech principles:

1. Heckman’s threat was itself a response to a threat by Judd, who had written this to Heckman earlier that day:

2. Both Judd’s implicit threat and Heckman’s explicit threat were all in the context of a negotiation. It’s not clear to me that Heckman saying, “I’ll do X for you but only if you do Y for me” should really count as suppression of freedom of speech.

What really bothered me about this story

What bothered me was not anything specific that Heckman wrote—the guy’s known to be a bit of a firebrand—but rather the starting point, which is that Judd was a coauthor of a paper that got negatively reviewed at a top journal, and then he just started pulling string after string to get it favorably reviewed and then accepted for publication!

Judd writes, “My goal was to make any rejection very difficult. The primary task was to hit back at the hostile referees who claimed that there was nothing new in our paper compared to published papers, presumably ones written by the referees.” I get the idea of being strategic in my dealings with journal article revisions, but I’ve never even imagined I could “make any rejection very difficult.” I mean, how can you do that? The journal editors can reject if they want, right?

I’m not saying it was wrong for the journal to publish the article—really, I have no idea, I have no sense of what sorts of things they want to publish—I’m just stunned that these sorts of tactics would even be on the table.

And what about this, from one of Judd’s emails to Heckman:

Last winter, I pleaded with you to proceed in a quick manner so that this paper could be accepted by now. In particular, a JPE paper is like winning the lottery for Lontzek in the European job market since none of his other papers are in a top journal. Instead, we waited until late August to hear from you, and now have to deal with six new referee reports, some very hostile. This means that Karl will have to support Lontzek for yet another year, sucking up money that he would like to use for other people.

I mean . . . I can’t even. I’ve contacted journal editors asking them to reconsider rejections of my submissions, and sometimes it even works. It doesn’t hurt to try. The decision is up to the editors, and if you send such a request, you’re just supplying them with more information. But to ask the decision to be made because it’s “like winning the lottery”? What does this say about the field of economics, or maybe academia more generally? And to plead for journal acceptance to save a third party from having to pay someone’s salary? This is a bit of sausage-making I wish I’d never seen.

I guess it’s still not as bad as some of the corruption in academic psychology (see discussion here)—it’s not corruption at all, exactly—it’s just soooo different from my experience. Not that someone would be upset at an unfair review process or ask for redress, but that this would really work, to the extent that the author and journal editor start negotiating over details, and with the suggestion that publication decisions be made based on the budgetary concerns of third parties . . . wow. Just wow.

I applaud Judd making all this public. I just wonder if he has a sense of how bizarre this all seems from the outside. Not just Heckman’s emails or his emails—I get that both sides in this dispute were frustrated and angry, and a lot of us will say or write rash things in a fit of passion—but rather the idea that it’s just standard practice to negotiate publication in this way. I’ve been writing scientific articles for close to 40 years now, and I’ve never seen anything like it.

Jobs using statistical modeling (including Stan) in biotech!

Nathan Sanders writes:

Montai Health is an early-stage biotechnology company developing a platform for understanding and leveraging complex molecular interactions within organisms to solve global challenges in human health and sustainability. The company leverages a multidisciplinary approach that integrates tools ranging from machine learning and big data to multi-omics and high-throughput screening. Montai Health was founded in Flagship Pioneering’s venture creation engine has conceived and created companies such as Moderna Therapeutics (NASDAQ: MRNA). Montai’s computational modeling group performs original model development ranging from Bayesian statistical modeling (using Stan!) of non-linear biological responses to machine learning with deep graph convolutional models and sequence representation models using frameworks such as Pytorch. The open positions are in chemical machine learning and computational biology, with an emphasis on sequence modeling.

And here are the two postings:

Job Application for Computational Biologist – Sequence Modeling at Flagship Pioneering, Inc., Cambridge, MA

Job Application for Machine Learning Scientist – Computational Chemistry at Flagship Pioneering, Inc., Cambridge, MA

Looks cool!

Full disclosure: I’ve done a little bit of consulting for these people.

Postdoc, research fellow, and doctoral student positions in ML / AI / Bayes in Finland

This job advertisement is by Aki

Postdoc, research fellow and doctoral researcher positions in machine learning artificial intelligence and Bayesian statistics – Finnish Center for Artificial Intelligence FCAI (Helsinki, Finland)

I (Aki) am also part of FCAI, and the positions would be at Aalto University or University of Helsinki. Although the call headline says AI and ML, plenty of topics are related to Bayesian inference, workflows, diagnostics, etc. (and according to EU memorandum 2021 Bayesian inference is part of AI). We already have many Stan, PyMC, and ArviZ developers, we’re contributing to many R and Python Bayesian probabilistic modeling and workflow packages, and of course we’re collaborating with Andrew. This is a great opportunity to contribute to improving Bayesian workflows (and ML/AI/etc). You can watch my talk for more about research ideas for workflows and you can check more about the other topics in the call link below.

FCAI’s internationally acclaimed research community provides you with a broad range of possibilities and Finland is a great place for living – it has been listed as the happiest country in the world for the fourth year running.

The deadline for the postdoc/research fellow applications is January 30 and for the doctoral researcher applications February 6, 2022 (23:59, UTC+2).

Read more and apply here: Researcher positions in AI/ML/Bayes — FCAI

Stan for the climate!

Thom Laepple writes:

I would like to draw your attention to the opening of two senior scientist and two postdoc positions in the Polar Terrestrial Environmental Systems section to complement the Earth System Diagnostics Team at the AWI (http://www.awi.de/) research centre in Potsdam, Germany
We are offering
One position for a statistician (with tenure track option) to optimally interpret complex and small sample size environmental datasets (such as paleoclimate data)
One position for a senior scientist on theoretical and stochastic modelling of Earth System processes (climate & paleoclimate archives)
Further, we are offering two two year PostDoc positions related to the ERC Starting Grant SPACE (Space time structure of climate change) of T. Laepple
Postdoc in ice-core research / statistical data analysis (m/f/d)
Ideally, the candidate has experience with time-series analysis in the time and spectral domain and ice-core data.
Postdoc in tree-ring research / tree ring data analysis
Ideally, the candidate has experience in the analysis of large-scale tree ring networks

Here’s some description from the above links:

You will develop and apply statistical tools to optimally interpret complex and small sample size environmental datasets. One example is the reconstruction of climate fields from sparse paleoclimate proxy measurements from ice-cores and sediment cores. You will further teach and consult researchers at AWI on statistical analysis. Ideally, you will successfully apply for a third-party funded junior research group to further boost the topic of climate/environmental data statistics@AWI.

You will:
– Develop and apply Bayesian calibrations of environmental proxies to translate raw proxy ‘sensor’ data into physical/biological quantities
– Develop and apply field reconstructions from sparse and time uncertain data that allows to integrate proxy ‘sensor’ data and climate fields.
– Implement prototypes of digital tools such as proxy forward models / artificial core generators that can be integrated in O2A
– Design optimal sampling and measurement procedures.

Looks interesting.

Summer internships at Flatiron Institute’s Center for Computational Mathematics

[Edit: Sorry to say this to everyone, but we’ve selected interns for this summer and are no longer taking applications. We’ll be taking applications again at the end of 2022 for positions in summer 2023.]

We’re hiring a crew of summer interns again this summer. We are looking for both undergraduates and graduate students. Here’s the ad.

I’m afraid the pay is low, but to make up for it, we cover travel, room, and most board (3 meals/day, 5 days/week). Also, there’s a large cohort of interns every summer across the five institutes at Flatiron (biology, astrophysics, neuroscience, quantum physics, and math), so there are plenty of peers with whom to socialize. Another plus is that we’re in a great location, on Fifth Avenue just south of the Flatiron Building (in the Flatiron neighborhood, which is a short walk to NYU in Greenwich Village and Google in Chelsea as well as to Times Square and the Hudson River Park).

If you’re interested in working on stats, especially applied Bayesian stats, Bayesian methodology, or Stan, please let me know via email at [email protected] so that I don't miss your application. We have two other Stan devs here, Yuling Yao (postdoc) and Brian Ward (software engineer).

We're also hiring full-time permanent research scientists at both the junior level and senior level, postdocs, and software engineers. For more on those jobs, see my previous post on jobs at Flatiron. That post has lots of nice photos of the office, which is really great. Or check out Google's album of photos.

Open positions in the Columbia statistics department

We have several research and teaching positions at Columbia Statistics, in all areas of the department.

Cool! As regular readers know, lots of interesting work is going on here in the statistics department; also there are lots of research connections and collaboration opportunities throughout the university.

P.S. In the earlier version of the post these were listed as postdoc positions, but that unofficial label seemed to be causing confusion, so I’ve simplified the description. All relevant information should be at the above link.