Casual Inference

Follow Regression to the Mean Girls on [⁠Apple Podcasts⁠], [⁠Spotify⁠], or wherever you love to listen!

Christine Zhang⁠ (⁠New York Times⁠) joins ⁠⁠⁠Sarah Lotspeich⁠⁠⁠ and ⁠⁠⁠Lucy D'Agostino McGowan⁠⁠⁠⁠ with a data-driven side quest into the TV show Law and Order. 

Check out the full analysis here: ⁠⁠⁠regressiontothemeangirls.com⁠⁠⁠

Links to content we chat about on the episode:

• ⁠Wrong Number newsletter⁠
• ⁠The Speed of Justice, According to Law & Order⁠

Follow along on instagram: 

⁠@regressiontothemeangirls

Follow Regression to the Mean Girls on [Apple Podcasts], [Spotify], or wherever you love to listen!

⁠Lucy D'Agostino McGowan⁠⁠ and ⁠⁠Sarah Lotspeich⁠⁠ return with a data-driven side quest into the TV show Severance. Lucy analyzes whether Milchick really uses more complicated language than his colleagues.

Check out the full analysis here: ⁠⁠regressiontothemeangirls.com⁠⁠

Links to content we chat about on the episode:

• ⁠⁠Lucy's Severance data R package [mdr]⁠⁠
• ⁠⁠Lucy's other Severance analyses⁠⁠
• ⁠⁠Dunnet⁠⁠
• ⁠⁠Radial plot of who is speaking in Severance ⁠⁠

Follow along on instagram: 

@regressiontothemeangirls

Sarah Lotspeich⁠ and ⁠Lucy D'Agostino McGowan⁠ introduce Regression to the Mean Girls, a podcast about data-driven side quests in pop culture. In this episode, Sarah analyzes 45 recent romance novels to find out how different romance tropes affect the timing of the couple’s first kiss.

Check out the full analysis here: ⁠https://regressiontothemeangirls.com/⁠

Links to content we chat about on the episode:

• ⁠Edward L. Kaplan and the Kaplan-Meier Survival Curve⁠
• ⁠Nonparametric Estimation from Incomplete Observations⁠
• ⁠Not just love, actually: why romance fiction is booming⁠
• ⁠What is the lipstick index?⁠

Follow along on instagram:

@regressiontothemeansgirls

Podcast feed: https://creators.spotify.com/pod/profile/rttmg/

• Emily: ‪@emilyriederer.bsky.social‬
• Ellie: @epiellie.bsky.social
• Lucy: @lucystats.bsky.social

Carly Brantner is an assistant professor of Biostatistics & Bioinformatics at Duke University and Duke Clinical Research Institute.

• multicate: R package for estimating conditional average treatment effects across one or more studies using machine learning methods
• PCORnet® Front Door: Access point for potential investigators, patient groups, and other stakeholders to connect with PCORnet and get support for potential research studies
• Patient-Centered Outcomes Data Repository (PDOCR): De-identified data from 24 (and counting) PCORI-funded studies

• Carly: @carlybrantner.bsky.social
• Ellie: @epiellie.bsky.social
• Lucy: @lucystats.bsky.social

• Vincent's "What is your estimand" section in his {marginaleffects} book: https://marginaleffects.com/chapters/challenge.html#sec-goals_estimand
• Article on defining estimands: https://doi.org/10.1177/00031224211004187
• Andrew's marginal effects post: https://www.andrewheiss.com/blog/2022/05/20/marginalia/
• Andrew's post on "fixed effects" and mariginal effects across different disciplines: https://www.andrewheiss.com/blog/2022/11/29/conditional-marginal-marginaleffects/

• Andrew: @andrew.heiss.phd
• Ellie: @epiellie.bsky.social
• Lucy: @lucystats.bsky.social

In this episode Lucy and Ellie dig into a recently publicized paper, "Vaccination and Neurodevelopmental Disorders: A Study of Nine-Year-Old Children Enrolled in Medicaid", which has gained attention after being promoted by RFK Jr. as evidence that vaccines cause autism.   

Ellie breaks down her Substack critique of the study. Together, she and Lucy discuss the methodological flaws and what a better version of this study might look like.  

• Vaccination and Neurodevelopmental Disorders: A Study of Nine-Year-Old Children Enrolled in Medicaid: https://publichealthpolicyjournal.com/vaccination-and-neurodevelopmental-disorders-a-study-of-nine-year-old-children-enrolled-in-medicaid/
• RFK Jr is promoting a new study claiming "vaccines cause autism" but it doesn't add up. Literally [Ellie's substack]: https://epiellie.substack.com/p/rfk-jr-is-promoting-a-new-study-claiming

Follow along on Bluesky:

• Ellie: @epiellie.bsky.social
• Lucy: @lucystats.bsky.social

🎶 Our intro/outro music is courtesy of Joseph McDade. Edited by Cameron Bopp.

• Vincent's website: https://arelbundock.com/
• Vincent's book "Model to Meaning: How to Interpret Statistical Models With marginaleffects for R and Python": https://marginaleffects.com/

• Vincent: @vincentab.bsky.social
• Ellie: @epiellie.bsky.social
• Lucy: @lucystats.bsky.social

Noah Greifer is a statistical consultant and programmer at Harvard University.

Episode notes:

• WeightIt package: https://ngreifer.github.io/WeightIt/
• MatchIt package: https://kosukeimai.github.io/MatchIt/
• Noah's awesome Stack Exchange post: https://stats.stackexchange.com/a/544958

Follow along on Bluesky:

• Noah: @noahgreifer.bsky.social
• Ellie: @EpiEllie.bsky.social
• Lucy: @LucyStats.bsky.social

🎶 Our intro/outro music is courtesy of Joseph McDade. Edited by Cameron Bopp.

Lucy and Ellie chat about large language models, chat interfaces, and causal inference.

• Do LLMs Act as Repositories of Causal Knowledge?: https://arxiv.org/html/2412.10635v1

Follow along on Twitter:

• The American Journal of Epidemiology: @AmJEpi

• Ellie: @EpiEllie

• Lucy: @LucyStats

🎶 Our intro/outro music is courtesy of Joseph McDade. Edited by Cameron Bopp.

Lucy chats with Len Testa about a recent analysis he did which combined over 150 publicly available data sources to answer a question about the affordability of Disney World.

• Len's Deep Dive Post on the Touring Plans Blog [Blog Post]
• Wall Street Journal Artcile, "Even Disney Is Worried About the High Cost of a Disney Vacation" [Article]

Follow along on Bluesky:

• Len: @lentesta.bsky.social

• Ellie: @EpiEllie.bsky.social

• Lucy: @LucyStats.bsky.social

🎶 Our intro/outro music is courtesy of Joseph McDade

Alyssa Bilinski, Peterson Family Assistant Professor of Health Policy, and Assistant Professor of Biostatistics, at Brown University School of Public Health. Her research focuses on developing novel methods for policy evaluation and applying these to identify interventions that most efficiently improve population health and well-being.

Episode notes:

• PNAS paper: https://www.pnas.org/doi/full/10.1073/pnas.2302528120

• Shuo Feng's pre-print: https://www.medrxiv.org/content/10.1101/2024.04.08.24305335v1

• Our uncertainty paper: https://pubmed.ncbi.nlm.nih.gov/33475686/

Follow along on Twitter:

• Alyssa: @ambilinski

• The American Journal of Epidemiology: @AmJEpi

• Ellie: @EpiEllie

• Lucy: @LucyStats

🎶 Our intro/outro music is courtesy of Joseph McDade
Edited by Cameron Bopp

Edward Kennedy Associate Professor, Department of Statistics & Data Science, Carnegie Mellon.

• ehkennedy.com

• Evaluating a Targeted Minimum Loss-Based Estimator for Capture-Recapture Analysis: An Application to HIV Surveillance in San Francisco, California: https://academic.oup.com/aje/article/193/4/673/7425624

• Doubly Robust Capture-Recapture Methods for Estimating Population Size: https://www.tandfonline.com/doi/full/10.1080/01621459.2023.2187814

Follow along on Twitter:

• The American Journal of Epidemiology: @AmJEpi

• Ellie: @EpiEllie

• Lucy: @LucyStats

🎶 Our intro/outro music is courtesy of Joseph McDade
Edited by Cameron Bopp

Sheree Bekker & Stephen Mumford are Co-directors of the Feminist Sport Lab and have a book coming soon: "Open Play: the case for feminist sport", coming Spring 2025. Reaktion Books (UK), University of Chicago Press (US).

Sheree Bekker: Associate Professor, University of Bath, Department for Health,

• Centre for Qualitative Research

• Centre for Health and Injury and Illness Prevention in Sport

Stephen Mumford, Professor of Metaphysics, Durham University  A

• Author of Dispositions (Oxford, 1998), Russell on Metaphysics (Routledge, 2003), Laws in Nature (Routledge, 2004), David Armstrong (Acumen, 2007), Watching Sport: Aesthetics, Ethics and Emotion (Routledge, 2011), Getting Causes from Powers (Oxford, 2011 with Rani Lill Anjum), Metaphysics: a Very Short Introduction (Oxford, 2012) and Causation: a Very Short Introduction (Oxford, 2013 with Rani Lill Anjum). I was editor of George Molnar's posthumous Powers: a Study in Metaphysics (Oxford, 2003) and Metaphysics and Science (Oxford, 2013 with Matthew Tugby).

• Feminist Sport Lab: https://www.feministsportlab.com

• Causation: A Very Short Introduction by Stephen Mumford & Rani Lill Anjum: https://academic.oup.com/book/616

• Faye Norby, Iditarod champion & epidemiologist: https://www.kfyrtv.com/2024/03/28/faye-norby-finishes-iditarod-trail-womens-foot-champion/?outputType=amp 

Follow along on Twitter:

• The American Journal of Epidemiology: @AmJEpi

• Ellie: @EpiEllie

• Lucy: @LucyStats

🎶 Our intro/outro music is courtesy of Joseph McDade
Edited by Cameron Bopp

Erick Scott is founder of cStructure, a causal science startup. Erick has expertise in medicine, public health, and computational biology.

• info@cStructure.io

• "A causal roadmap for generating high-quality real-world evidence" https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10603361/

Follow along on Twitter:

• The American Journal of Epidemiology: @AmJEpi

• Ellie: @EpiEllie

• Lucy: @LucyStats

🎶 Our intro/outro music is courtesy of Joseph McDade
Edited by Cameron Bopp

Nima Hejazi is an assistant professor in biostatistics at Harvard University. His methodological work often draws upon tools and ideas from semi- and non-parametric inference, high-dimensional and large-scale inference, targeted or debiased machine learning (e.g., targeted minimum loss estimation, method of sieves), and computational statistics.

• Surprised by the Hot Hand Fallacy? A Truth in the Law of Small Numbers by Joshua B. Miller & Adam Sanjurjo: https://www.jstor.org/stable/44955325

• Nima is on Twitter/X as @nshejazi (https://twitter.com/nshejazi) and my academic webpage is https://nimahejazi.org

• Recent translational review paper (intended for the infectious disease science community) I was involved in describing some causal/statistical frameworks for evaluating immune markers as mediators / surrogate endpoints: https://pubmed.ncbi.nlm.nih.gov/38458870/

• The tlverse software ecosystem is on GitHub at https://github.com/tlverse and the tlverse handbook is freely available at https://tlverse.org/tlverse-handbook/

• Dr. Hejazi annually co-teaches a causal mediation analysis workshop at SER, and notes from the latest offering are freely available at https://codex.nimahejazi.org/ser2023_mediation_workshop/

Follow along on Twitter:

• The American Journal of Epidemiology: @AmJEpi

• Ellie: @EpiEllie

• Lucy: @LucyStats

🎶 Our intro/outro music is courtesy of Joseph McDade
Edited by Cameron Bopp

Aaditya Ramdas is an assistant professor at Carnegie Mellon University, in the Departments of Statistics and Machine Learning. His research interests include game-theoretic statistics and sequential anytime-valid inference, multiple testing and post-selection inference, and uncertainty quantification for machine learning (conformal prediction, calibration). His applied areas of interest include neuroscience, genetics and auditing (real-estate, finance, elections). Aaditya received the IMS Peter Gavin Hall Early Career Prize, the COPSS Emerging Leader Award, the Bernoulli New Researcher Award, the NSF CAREER Award, the Sloan fellowship in Mathematics, and faculty research awards from Adobe and Google. He also spends 20% of his time at Amazon working on causality and sequential experimentation.

• Aaditya's website: https://www.stat.cmu.edu/~aramdas/

• Game theoretic statistics resources

  • Aaditya's course, Game-theoretic probability, statistics, and learning:

    • https://www.stat.cmu.edu/~aramdas/gtpsl/index.html

  • Papers of interest:

    • Time-uniform central limit theory and asymptotic confidence sequences: https://arxiv.org/abs/2103.06476

    • Game-theoretic statistics and safe anytime-valid inference: https://arxiv.org/abs/2210.01948

  • Discussion papers:

    • Safe Testing: https://arxiv.org/abs/1906.07801

    • Testing by Betting: https://academic.oup.com/jrsssa/article/184/2/407/7056412

    • Estimating means of bounded random variables by betting: https://academic.oup.com/jrsssb/article/86/1/1/7043257 

Follow along on Twitter:

• The American Journal of Epidemiology: @AmJEpi

• Ellie: @EpiEllie

• Lucy: @LucyStats

🎶 Our intro/outro music is courtesy of Joseph McDade
Edited by Cameron Bopp

Ingrid is a doctoral student in Epidemiology at the Dalla Lana School of Public Health at the University of Toronto. 

• Winning cookie recipe

Follow along on Twitter:

• The American Journal of Epidemiology: @AmJEpi

• Ellie: @EpiEllie

• Lucy: @LucyStats

🎶 Our intro/outro music is courtesy of Joseph McDade
Edited by Cameron Bopp

Nick Huntington-Klein is an Assistant Professor, Department of Economics, Albers School of Business and Economics, Seattle University. His research focus is econometrics, causal inference, and higher education policy. He's also the author of an introductory causal inference textbook called The Effect and the creator of a number of Stata packages for implementing causal effect estimation procedures.

• Nick's book, online version: https://theeffectbook.net/

• The Paper of How: https://onlinelibrary.wiley.com/share/W2FMEESMMSJMWDEZYY8Y?target=10.1111/obes.12598

• Nick's twitter & BlueSky: @nickchk

• Nick's website: https://nickchk.com

Follow along on Twitter:

• The American Journal of Epidemiology: @AmJEpi

• Ellie: @EpiEllie

• Lucy: @LucyStats

🎶 Our intro/outro music is courtesy of Joseph McDade
Edited by Cameron Bopp

• The Clone-Censor-Weight Method in Pharmacoepidemiologic Research: Foundations and Methodological Implementation: https://link.springer.com/article/10.1007/s40471-024-00346-2 

• Immortal time in pregnancy: https://pubmed.ncbi.nlm.nih.gov/36805380/ 

Follow along on Twitter:

• The American Journal of Epidemiology: @AmJEpi

• Ellie: @EpiEllie

• Lucy: @LucyStats

🎶 Our intro/outro music is courtesy of Joseph McDade
Edited by Cameron Bopp

Mark van der Laan is a professor of statistics at the University of California, Berkeley. His research focuses on developing statistical methods to estimate causal and non-causal parameters of interest, based on potentially complex and high dimensional data from randomized clinical trials or observational longitudinal studies, or from cross-sectional studies. 

• Center for Targeted Learning, Berkeley: https://ctml.berkeley.edu/

• A causal roadmap: https://pubmed.ncbi.nlm.nih.gov/37900353/ 

• Short course on causal learning: https://ctml.berkeley.edu/introduction-causal-inference 

• Handbook on the TLverse (Targeted Learning in R): https://ctml.berkeley.edu/publications/targeted-learning-handbook-causal-machine-learning-and-inference-tlverse-r-software 

• Mark on twitter: @mark_vdlaan

Follow along on Twitter:

• The American Journal of Epidemiology: @AmJEpi

• Ellie: @EpiEllie

• Lucy: @LucyStats

🎶 Our intro/outro music is courtesy of Joseph McDade
Edited by Cameron Bopp

Ellie and Lucy kick off the season and introduce our new executive buzzer, Melita! Melita is a masters student in statistics at Wake Forest University and will be helping out with the podcast (and keeping Lucy and Ellie from using too much jargon!)

Pros & Cons of RCT paper: 

• Fernainy, P., Cohen, A.A., Murray, E. et al. Rethinking the pros and cons of randomized controlled trials and observational studies in the era of big data and advanced methods: a panel discussion. BMC Proc 18 (Suppl 2), 1 (2024). https://doi.org/10.1186/s12919-023-00285-8

Follow along on Twitter:

• The American Journal of Epidemiology: @AmJEpi

• Ellie: @EpiEllie

• Lucy: @LucyStats

🎶 Our intro/outro music is courtesy of Joseph McDade
Edited by Cameron Bopp

Ellie Murray and Lucy D'Agostino McGowan chat with Ralph D'Agostino Sr. and Ralph D'Agostino Jr. about their careers in statistics, looking back at how things have developed and forward at where they see the world of statistics and epidemiology going. 

Ralph D'Agostino Sr. was a professor of Mathematics/Statistics, Biostatistics, and Epidemiology at Boston University. He was the lead biostatistician for the Framingham Heart Study, a biostatistical consultant to The New England Journal of Medicine, an editor of Statistics in Medicine and lead editor of their Tutorials, and a member and consultant on FDA committees. His major fields of research were clinical trials, prognostic models, longitudinal analysis, multivariate analysis, robustness, and outcomes/effectiveness research. 

Ralph D'Agostino Jr. is a professor in the Department of Biostatistics and Data Science at Wake Forest University where he is the Director of the Biostatistics Core of the Comprehensive Cancer Center. Methodologically his research includes developing statistical techniques for evaluating data from observational settings, handling missing data in applied problems, and developing predictive functions to identify prospectively patients at elevated risk for future negative outcomes. Some of his recent work includes the development of methods using propensity score models to identify safety signals in large retrospective databases. 

Ellie and Lucy chat with Dr. Cat Hicks, VP of Research Insights and Director of Developer Success Lab at Pluralsight Flow, about evidence science. 

Follow along on Twitter:

• Cat: @grimalkina
• The American Journal of Epidemiology: @AmJEpi
• Ellie: @EpiEllie
• Lucy: @LucyStats

🎶 Our intro/outro music is courtesy of Joseph McDade
Edited by Quinn Rose: aspiringrobot.com

Lucy D'Agostino McGowan and Ellie Murray chat about a "Causal Quartet" and spend some extra time on M-Bias!

Lucy, Travis, & Malcom's Causal Quartet Paper

Lucy's quartets R package

Follow along on Twitter:

• The American Journal of Epidemiology: @AmJEpi
• Ellie: @EpiEllie
• Lucy: @LucyStats

🎶 Our intro/outro music is courtesy of Joseph McDade
Edited by Quinn Rose: aspiringrobot.com

Lucy D'Agostino McGowan and Ellie Murray chat about ENAR 2023 and Targeted Learning!

Targeted Learning in R Handbook

Follow along on Twitter:

• The American Journal of Epidemiology: @AmJEpi
• Ellie: @EpiEllie
• Lucy: @LucyStats

🎶 Our intro/outro music is courtesy of Joseph McDade
Edited by Quinn Rose: aspiringrobot.com

Lucy D'Agostino McGowan and Ellie Murray chat with #EpiCookieChallenge winner, Viktoria Gastens!

Follow along on Twitter:

• The American Journal of Epidemiology: @AmJEpi
• Viktoria: @VikiGastens
• Viktoria's Lab: @PopHealthLabCH
• Ellie: @EpiEllie
• Lucy: @LucyStats

🎶 Our intro/outro music is courtesy of Joseph McDade
Edited by Quinn Rose: aspiringrobot.com

Lucy D'Agostino McGowan and Ellie Murray chat about confounding!

✍️ Lucy's new paper: Sensitivity Analyses for Unmeasured Confounders

Follow along on Twitter:

• The American Journal of Epidemiology: @AmJEpi
• Ellie: @EpiEllie
• Lucy: @LucyStats

🎶 Our intro/outro music is courtesy of Joseph McDade
Edited by Quinn Rose: aspiringrobot.com

Lucy D'Agostino McGowan and Ellie Murray chat about randomized controlled trials, thinking about efficacy vs effectiveness and saftey vs safetiness.

✍️ Frank Harrell's blog post "Randomized Clinical Trials Do Not Mimic Clinical Practice, Thank Goodness"

Follow along on Twitter:

• The American Journal of Epidemiology: @AmJEpi
• Ellie: @EpiEllie
• Lucy: @LucyStats

🎶 Our intro/outro music is courtesy of Joseph McDade
Edited by Quinn Rose: aspiringrobot.com

Lucy D'Agostino McGowan and Ellie Murray chat with Maria Glymour, Professor of Epidemiology & Biostatstics at UCSF and incoming chair of the Department of Epidemiology at Boston University. Maria successfully convinces Ellie and Lucy that instrumental variables can be very useful in epidemiology. 

Follow up:

✍️ Andrew Heiss's blog post on marginal and conditional effects for GLMMs

Follow along on Twitter:

• Maria Glymour: @MariaGlymour
• The American Journal of Epidemiology: @AmJEpi
• Ellie: @EpiEllie
• Lucy: @LucyStats

🎶 Our intro/outro music is courtesy of Joseph McDade
Edited by Quinn Rose: aspiringrobot.com

Lucy D'Agostino McGowan and Ellie Murray chat about critiquing methods research, average treatment effects, and positivity violations!

Follow along on Twitter:

• The American Journal of Epidemiology: @AmJEpi
• Ellie: @EpiEllie
• Lucy: @LucyStats

🎶 Our intro/outro music is courtesy of Joseph McDade

Lucy D'Agostino McGowan and Ellie Murray chat with Travis Gerke, Director of Data Science at The Prostate Cancer Clinical Trials Consortium (PCCTC). This episode has lots of hot takes and lots of love for logistic regression!

Follow along on Twitter:

• Travis Gerke: @travisgerke
• The American Journal of Epidemiology: @AmJEpi
• Ellie: @EpiEllie
• Lucy: @LucyStats

🎶 Our intro/outro music is courtesy of Joseph McDade
Edited by Quinn Rose: aspiringrobot.com

Lucy D'Agostino McGowan and Ellie Murray chat about counterfactuals!

Follow along on Twitter:

• The American Journal of Epidemiology: @AmJEpi
• Ellie: @EpiEllie
• Lucy: @LucyStats

🎶 Our intro/outro music is courtesy of Joseph McDade
Edited by Quinn Rose: aspiringrobot.com

In this episode Ellie Murray and Lucy D'Agostino McGowan chat with Enrique Schisterman, Perelman Professor and Chair of the Department of Biostatistics, Epidemiology, and Informatics at the University of Pennsylvania, about the future of epidemiology.

Follow along on Twitter:

• Enrique: @eschisterman1
• The American Journal of Epidemiology: @AmJEpi
• Ellie: @EpiEllie
• Lucy: @LucyStats

🎶 Our intro/outro music is courtesy of Joseph McDade

In this episode we play the audio from a recent panel discussion co-sponsored by UNC TraCS, Duke University and Wake Forest U CTSA Biostatistics, Epidemiology and Research Design (BERD) Cores. The panelists were Charles Poole (Associate Professor of Epidemiology, UNC) Lucy D'Agostino McGowan, and Charles Scales (Associate Professor of Surgery, Duke University) and it was facilitated by Marcella Boynton (Assistant Professor, General Internal Medicine, UNC/NC TraCS).

🎥 The video of the panel can be found here

🎞 Lucy's slides

📃 The ASA Statement on p-values

📃 The American Statistician issue on p-values following the SSI conference

Follow along on Twitter:

• The American Journal of Epidemiology: @AmJEpi
• Ellie: @EpiEllie
• Lucy: @LucyStats

🎶 Our intro/outro music is courtesy of Joseph McDade

In this episode Lucy D'Agostino McGowan and Ellie Murray chat with Sander Greenland, Emeritus Professor of Epidemiology and Statistics at UCLA.

Follow along on Twitter:

• The American Journal of Epidemiology: @AmJEpi
• Ellie: @EpiEllie
• Lucy: @LucyStats

🎶 Our intro/outro music is courtesy of Joseph McDade
Edited by Quinn Rose: aspiringrobot.com

In this episode Lucy D'Agostino McGowan and Ellie Murray chat with Toyya Pujol, Operations Researcher at RAND Corporation.

Follow along on Twitter:

• Toyya: @toyyapujol
• The American Journal of Epidemiology: @AmJEpi
• Ellie: @EpiEllie
• Lucy: @LucyStats

In this episode Lucy D'Agostino McGowan and Ellie Murray chat with Maggie Makar, Presidential postdoctoral fellow and assistant professor in Computer Science and Engineering at the University of Michigan.

Follow along on Twitter:

• Maggie: @Maggiemakar
• The American Journal of Epidemiology: @AmJEpi
• Ellie: @EpiEllie
• Lucy: @LucyStats

Slide link: https://bit.ly/3DnQai5

🎶 Our intro/outro music is courtesy of Joseph McDade
Edited by Quinn Rose: aspiringrobot.com

In this episode Lucy D'Agostino McGowan and Ellie Murray chat with Judea Pearl, Chancellor professor of computer science and statistics at the University of California, Los Angeles.

📄 Judea's recent papers

📖 Book of Why

Follow along on Twitter:

• Judea: @yudapearl
• The American Journal of Epidemiology: @AmJEpi
• Ellie: @EpiEllie
• Lucy: @LucyStats

Slide link: https://bit.ly/3DnQai5

🎶 Our intro/outro music is courtesy of Joseph McDade

In this episode Lucy D'Agostino McGowan and Ellie Murray chat with #EpiCookieChallenge winner, Chris Schaich about the epidemiologist John Snow. Dr. Schaich is an assistant professor at Wake Forest School of Medicine in the Hypertension and Vascular Research Center.

Follow along on Twitter:

• Chris: @Chris_Schaich
• The American Journal of Epidemiology: @AmJEpi
• Ellie: @EpiEllie
• Lucy: @LucyStats

Slide link: https://bit.ly/3DnQai5

🎶 Our intro/outro music is courtesy of Joseph McDade

In this episode Lucy D'Agostino McGowan and Ellie Murray chat about their Spotify Wrapped for Casual Inference, and Ellie Murray talks about causal inference for complex data with the University of Minnesota's epidemiology department.

Follow along on Twitter:

• The American Journal of Epidemiology: @AmJEpi
• Ellie: @EpiEllie
• Lucy: @LucyStats

Slide link: https://bit.ly/3DnQai5

Transcript (auto-generated): https://bit.ly/3y4OskQ

🎶 Our intro/outro music is courtesy of Joseph McDade.

In this episode Lucy D'Agostino McGowan and Ellie Murray chat about the history of causal inference, tracing the origins across disciplines from statistics to economics, epidemiology, and computer science, discussing contributions from Rubin, Robins, Pearl, and more!

Follow along on Twitter:

• The American Journal of Epidemiology: @AmJEpi
• Ellie: @EpiEllie
• Lucy: @LucyStats

🎶 Our intro/outro music is courtesy of Joseph McDade.

In this episode Lucy D'Agostino McGowan and Ellie Murray chat with Hilary Parker about design thinking for data analysis, the Dunning-Kruger effect, and the potential data behind baby Yoda.

Follow along on Twitter:

• Hilary: @hspter
• The American Journal of Epidemiology: @AmJEpi
• Ellie: @EpiEllie
• Lucy: @LucyStats

🎶 Our intro/outro music is courtesy of Joseph McDade.

In this episode Lucy D'Agostino McGowan and Ellie Murray chat with Noah Haber about metascience, causal language in the literature, and more!

🥇 Causal Inference Nobel Prize Press Release

📝 Causal and Associational Linking Language From Observational Research and Health Evaluation Literature in Practice: A systematic language evaluation

📝 What Should Researchers Expect When They Replicate Studies? A Statistical View of Replicability in Psychological Science

📝 Design principles of data analysis

📝 Causal language and strength of inference in academic and media articles shared in social media (CLAIMS): A systematic review

🔗 Reading past headlines [part 1]

🔗 Reading past headlines [part 2]

Follow along on Twitter:

• Noah: @NoahHaber
• The American Journal of Epidemiology: @AmJEpi
• Ellie: @EpiEllie
• Lucy: @LucyStats

🎶 Our intro/outro music is courtesy of Joseph McDade.

In this episode Lucy D'Agostino McGowan and Ellie Murray chat with Len Testa, president of TouringPlans, about solving optimization problems in travel and healthcare.

📦 Lucy's R package with touringplans data

Len's slide on model choices:

Follow along on Twitter:

• Len: @LenTesta
• The American Journal of Epidemiology: @AmJEpi
• Ellie: @EpiEllie
• Lucy: @LucyStats

🎶 Our intro/outro music is courtesy of Joseph McDade.

In this episode Lucy D'Agostino McGowan and Ellie Murray chat with Ashley Buchanan about causal inference with a focus on networks. Dr. Buchanan is an assistant professor of Biostatistics in the Department of Pharmacy Practice at the University of Rhode Island.

🔗 Dr. Buchanan's website

Follow along on Twitter:

• The American Journal of Epidemiology: @AmJEpi
• Ellie: @EpiEllie
• Lucy: @LucyStats

🎶 Our intro/outro music is courtesy of Joseph McDade.

In this episode Ellie Murray and Lucy D'Agostino McGowan do a series recap and then discuss sensitivity, specificity, and appropriate messaging in the context of coronavirus rapid tests.

📝 Evaluation of the Abbott BinaxNOW rapid antigen test for SARS-CoV-2 infection in children: Implications for screening in a school setting

📝 NY Times article: One in 5,000

🐦 Kareem Carr's tweet about omitted variable bias in randomized controlled trials

📝 Israeli data: How can efficacy vs. severe disease be strong when 60% of hospitalized are vaccinated?

🦠 A calculator that lets you estimate COVID risk [microcovid]

In the (Local) News

📰 Will Podcasting and Social Media Replace Journals and Traditional Science Communication? No, but...

Follow along on Twitter:

• The American Journal of Epidemiology: @AmJEpi
• Ellie: @EpiEllie
• Lucy: @LucyStats

🎶 Our intro/outro music is courtesy of Joseph McDade.

👩‍🎨 Our artwork is by Allison Horst.

In this 23rd episode of Casual Inference Ellie Murray and Lucy D'Agostino McGowan chat about fixed vs random effect, complete a statistics challenge, and talk about DAGs.

🐦 Tweet from @jtc475 about fixed vs random effects terminology

🎲 This is Statistics March Randomness Challenge

📝 Lucy, Kyra, and Ellie's paper "Quantifying Uncertainty in Infectious Disease Mechanistic Models"

PeDAGogy

Here are the two Bridgerton DAGs we discussed.

1. Tweet submitted by @IGMoore: 

2. Tweet submitted by @AlenaSorensen

Follow along on Twitter:

• The American Journal of Epidemiology: @AmJEpi
• Ellie: @EpiEllie
• Lucy: @LucyStats

🎶 Our intro/outro music is courtesy of Joseph McDade.

👩‍🎨 Our artwork is by Allison Horst.

In this episode Ellie Murray and Lucy D'Agostino McGowan chat with Julia Raifman about health policy, a recent study on unemployment insurance and food insecurity, and anti racism in academia. Dr. Raifman is an assistant professor of Health Law, Policy, and Management at Boston University. Her research focuses on how health and social policies drive population health and health disparities.

📝 Geoffrey Rose's paper Sick Individuals and Sick Populations

📝Julia's recent paper - Association Between Receipt of Unemployment Insurance and Food Insecurity Among People Who Lost Employment During the COVID-19 Pandemic in the United States

PeDAGogy

Come up with a Bridgerton DAG and share it with us on Twitter! Here is one for inspiration.  

Me: "Hi please fund me to do innovative research"

Also me: "Sure I'll lead a DAG discussion on the @PWGTennant et al. @IJEeditorial paper... I'd like to focus on how offensively hot the guy from Bridgerton is."@mrc_ieu and @BristolTARG PhD student Mark Gibson made my day! pic.twitter.com/CFOoYhMGjt

— Gareth Griffith (@Garethjgriffith) February 1, 2021

Follow along on Twitter:

• The American Journal of Epidemiology: @AmJEpi
• Julia: @JuliaRaifman
• Ellie: @EpiEllie
• Lucy: @LucyStats

🎶 Our intro/outro music is courtesy of Joseph McDade.

👩‍🎨 Our artwork is by Allison Horst.

In this episode Ellie Murray and Lucy D'Agostino McGowan chat with Ralph D'Agostino Sr. and Ralph D'Agostino Jr. about their careers in statistics, looking back at how things have developed and forward at where they see the world of statistics and epidemiology going. We're excited to kick off the 100th year of the American Journal of Epidemiology with this episode.

Ralph D'Agostino Sr. is a professor of Mathematics/Statistics, Biostatistics, and Epidemiology at Boston University. He has been the lead biostatistician for the Framingham Heart Study, a biostatistical consultant to The New England Journal of Medicine, an editor of Statistics in Medicine and lead editor of their Tutorials, and a member and consultant on FDA committees. His major fields of research are clinical trials, prognostic models, longitudinal analysis, multivariate analysis, robustness, and outcomes/effectiveness research. 

Ralph D'Agostino Jr. is a professor in the Department of Biostatistics and Data Science at Wake Forest University where he is the Director of the Biostatistics Core of the Comprehensive Cancer Center. Methodologically his research includes developing statistical techniques for evaluating data from observational settings, handling missing data in applied problems, and developing predictive functions to identify prospectively patients at elevated risk for future negative outcomes. Some of his recent work includes the development of methods using propensity score models to identify safety signals in large retrospective databases. 

It also turns out they are Lucy's father and grandfather, so we have 3 generations of statisticians on the pod!

We also have Amit Sasson on to discuss the winning cookie from the #EpiCookieChallenge as well as her work in causal inference!

Follow along on Twitter:

• The American Journal of Epidemiology: @AmJEpi
• Ellie: @EpiEllie
• Lucy: @LucyStats

🎶 Our intro/outro music is courtesy of Joseph McDade.

👩‍🎨 Our artwork is by Allison Horst.