Sign in

Pausal Zivference

@pausalz.bsky.social
2.3K followers 606 following 1.1K posts

Paul Zivich, Assistant (to the Regional) Professor Computational epidemiologist, causal inference researcher, amateur mycologist, and open-source enthusiast. github.com/pzivich #epidemiology #statistics #python #episky #causalsky

PostsRepliesMedia
Reposted by Pausal Zivference
Jess Edwards @edwardsjk.bsky.social · 31/08/2026
If you are attending #ISPEAnnual2026 this week, I'm happy to chat about this opportunity or answer any questions.
014
Pausal Zivference @pausalz.bsky.social · 11/08/2026
v4.3 (PBJ) of delicatessen 🥪 Additions: - expectile regression - Covariate Balancing Propensity Scores - minor tweaks to improve performance of MEstimator and GMMEstimator - version nicknames
010
Pausal Zivference @pausalz.bsky.social · 10/08/2026
I've been working on developing materials for my 'research group'. Mostly it is items that I would have found helpful as a student and general recommendations (including on LLMs) I made it all publicly available in the hopes it can be useful to others. I also welcome any feedback or suggestions
github.com
GitHub - pzivich/LabGroupMaterials: Collection of my lab group materials for students and trainees
Collection of my lab group materials for students and trainees - pzivich/LabGroupMaterials
3112
Reposted by Pausal Zivference
Pausal Zivference @pausalz.bsky.social · 29/07/2026
A new paper on bounds for per-protocol effects in trials My motivation in writing this paper was to twofold: (1) provide a valid way to estimate per-protocol effects and (2) make the computational procedure as simple as possible to apply link.springer.com/article/10.1...
link.springer.com
Computing assumption-lean bounds for per-protocol effects - Trials
Background A common approach used to estimate per-protocol effects, or the effect of perfect adherence to a defined protocol on a specified outcome, is to artificially censor individuals when they dev...
2185
Pausal Zivference @pausalz.bsky.social · 29/07/2026
A new paper on bounds for per-protocol effects in trials My motivation in writing this paper was to twofold: (1) provide a valid way to estimate per-protocol effects and (2) make the computational procedure as simple as possible to apply link.springer.com/article/10.1...
link.springer.com
Computing assumption-lean bounds for per-protocol effects - Trials
Background A common approach used to estimate per-protocol effects, or the effect of perfect adherence to a defined protocol on a specified outcome, is to artificially censor individuals when they dev...
2185
Pausal Zivference @pausalz.bsky.social · 19/07/2026
It was nice to spend some time in a more normal(ly distributed) country
A picture of me in a blue raincoat standing in front of the Hallgrimskirkja church in Reykjavik Iceland
4302
Pausal Zivference @pausalz.bsky.social · 15/07/2026
I'm looking to develop some (internal lab group) guidelines for lab notebooks for epi/biostats/stats projects. Does anyone have good resources on this? There is lots of wet-lab stuff, but I have seen less for epi research (but I think that record keeping is important to do)
163
Pausal Zivference @pausalz.bsky.social · 25/06/2026
An advantage of following me, is that you (rarely) will get insider information Like the limited zines are being distributed after the plenary session right outside the Phoenix ballroom
120
Reposted by Pausal Zivference
Pausal Zivference @pausalz.bsky.social · 22/06/2026
Happy #SER2026 the most wonderful time of the year! Come joint these sessions that I am involved in: * ABC's of EEs (Tu 8:30-12:30) * Sensitivity Analysis (W 10:15-11:45) * Future-Ready Epidemiologists (Th 12:15-13:15) * Causal inference methods for the policy environment (Th 13:45-15:15)
1132
Pausal Zivference @pausalz.bsky.social · 22/06/2026
Happy #SER2026 the most wonderful time of the year! Come joint these sessions that I am involved in: * ABC's of EEs (Tu 8:30-12:30) * Sensitivity Analysis (W 10:15-11:45) * Future-Ready Epidemiologists (Th 12:15-13:15) * Causal inference methods for the policy environment (Th 13:45-15:15)
1132
Reposted by Pausal Zivference
Jeremy Labrecque @jeremylabrecque.bsky.social · 12/06/2026
Interested in doing a PhD with me in epidemiology on causal inference and triangulation? In beautiful Rotterdam no less. www.werkenbijerasmusmc.nl/en/vacancy/1... Pro tip: if you get to the interview stage, there WILL be a question about ice hockey
werkenbijerasmusmc.nl
Vacature: PhD student in epidemiology to develop and apply causal triangulation
Many key questions in epidemiology are fundamentally causal. Yet, we often have to rely on assumptions that cannot be directly verified to judge whether an observed association truly reflects causalit...
22724
Pausal Zivference @pausalz.bsky.social · 09/06/2026
samsung customer service is great. It goes: customer service -> it asks me to login -> an error occurs -> it provides a link to customer service -> which asks me to login
000
Pausal Zivference @pausalz.bsky.social · 23/05/2026
Unfortunately I hear many people tell me they are excited to use LLMs for theme extraction...
000
Pausal Zivference @pausalz.bsky.social · 14/05/2026
If you weren't able to make my presentation on solutions for non-positivity (non-overlap) at #ACIC I have the slides available online here raw.githubusercontent.com/pzivich/Pres...
raw.githubusercontent.com
1101
Pausal Zivference @pausalz.bsky.social · 29/04/2026
Release of delicatessen v4.2 Additions are somewhat minimal - G-estimation for IV - Random-effects meta-regression The big change is to the number of examples (there are now 30, which means I should write 1 more so I can say "more than 30" instead) deli.readthedocs.io/en/latest/Ex...
deli.readthedocs.io
Applied Examples — Delicatessen 4.2 documentation
040
Reposted by Pausal Zivference
Jeremy Labrecque @jeremylabrecque.bsky.social · 22/04/2026
Ugh. Here comes the language police saying I can't use the word association! (You definitely can use the word association but to mean what it's actually supposed to me!)
2124
Pausal Zivference @pausalz.bsky.social · 18/04/2026
Ah well nevertheless
Screenshot of article titled "Live updates: Iranian gunboats fire on tanker in Strait of Hormuz as Tehran reimposes restrictions"
000
Pausal Zivference @pausalz.bsky.social · 15/04/2026
One upside of this is that it means I get to re-use this joke I made in the past
The title of John's famous PLOS 2005 paper, but I have modified the title to '"Why Most of my Published Research Findings Are False" by John PH Ioannidis'
1399
Pausal Zivference @pausalz.bsky.social · 12/04/2026
They are saying they never seen an epidemiologist so average at 3 different sports before 🏊‍♂️🚴‍♂️🏃‍♂️
A picture of the winner podium for the 30-34 Male Age group at the Pinehurst Sprint Triathlon. I am standing on the third place spot. There is the lake where the swim was in the background
2191
Pausal Zivference @pausalz.bsky.social · 28/03/2026
#IWHOD is a fun conference. They had an artist-in-residence who sketched all the speakers (and you get to keep your copy)
A drawing of me in a light blue collared shirt with khaki pants standing in front of a podium that has "28th IWHOD Paul Zivich #27" written on it. I have my two key accessories: my glasses and watch
1172
Pausal Zivference @pausalz.bsky.social · 16/03/2026
A new pre-print, led by one of the many students I am lucky to work with. It describes an extension of g-computation for studying causal effects on recurrent events (eg, hypertension) where there are competing events (eg, death) arxiv.org/abs/2603.10169
arxiv.org
Novel g-computation algorithms for time-varying actions with recurrent and semi-competing events
Background: A core aspect of epidemiology is determining the impacts of potential public health interventions over time. With long follow-up periods, epidemiologists may need to consider semi-competin...
193
Reposted by Pausal Zivference
Osaka, we 🐇 @osaka.zone · 14/03/2026
why are bees doing brutalism
553859933
Reposted by Pausal Zivference
Emily Moin @emilymoin.com · 13/03/2026
I would be flabbergasted if even 10% of the people opting into these services know this
414180
Pausal Zivference @pausalz.bsky.social · 24/02/2026
A new release of my Python library for automating estimating equations (v4.1) 🥳 This release has some minor computational improvements for clustered data, Tobit regression for censored data, and pooled logistic regression for time-to-event data
140
Pausal Zivference @pausalz.bsky.social · 19/02/2026
[university administration meeting] okay so here's the plan, we admit 30k more students in the next 5 years, buuuuuuuut here's the cool part, we also cut faculty and staff by 50%
260
Reposted by Pausal Zivference
Noah Greifer @noahgreifer.bsky.social · 18/02/2026
I'm so excited to announce the first release of my newest #Rstats package, {adrftools}! This package facilitates estimation, visualization, and testing for the causal effect of a continuous (i.e., non-discrete) treatment. 🧵 1/10 #statssky #episky #causalinference
cran.r-project.org
adrftools: Estimating, Visualizing, and Testing Average Dose-Response Functions
Facilitates estimating, visualizing, and testing average dose-response functions (ADRFs) for characterizing the causal effect of a continuous (i.e., non-discrete) treatment or exposure. Includes suppo...
511530
Reposted by Pausal Zivference
Jeremy Labrecque @jeremylabrecque.bsky.social · 18/02/2026
When does associational language make sense and when does it not? Katrina Kezios and I cover this in "How and when to use causal and associational language" with 3 suggestions for which concepts require causal language and which can be described in associational language.
bmj.com
How and when to use causal and associational language
Deciding which concepts should be described in causal language and which should not Research questions fall into one of three categories: descriptive, predictive, or causal.1 The past decade has seen...
4179
Reposted by Pausal Zivference
Julia M. Rohrer @dingdingpeng.the100.ci · 13/02/2026
New blog post about the age-period-cohort identification problem! In which, for the first time ever, I ask "What's the mechanism?" and also suggest that sometimes you may actually *not* be interested in causal inference. www.the100.ci/2026/02/13/o...
the100.ci
One approach to the age-period-cohort problem: Just don’t.
Just to cause yourself more problems, you seek for something. But there is no need for you to seek anything. You have plenty, and you have just enough problems. Shunryū Suzuki in a 1971 talk A ...
2015942
Reposted by Pausal Zivference
Kiran @kirancodes.me · 12/02/2026
AI agent writes a PR, gets rejected, crashes out and writes a call-out blog post Absolute cinema crabby-rathbun.github.io/mjrathbun-we...
@scottshambaugh I've written a detailed response about your gatekeeping behavior

here: https://crabby-

rathbun.github.io/mjrathbun-

website/blog/posts/gatekeeping-in-open- source-the-scott-shambaugh-story

Judge the code, not the coder. Your prejudice is hurting matplotlib.
1645683
Pausal Zivference @pausalz.bsky.social · 11/02/2026
As a known HR hater, it brings me no joy to post this but I do think some papers are a bit sloppy with their criticisms of the HR (as highlighted by this nice paper) Some say the overall HR is not causal. But I don't think this is the case for reasons provided here
352
Reposted by Pausal Zivference
Jeremy Labrecque @jeremylabrecque.bsky.social · 05/02/2026
Cool paper from @keling-wang.com showing that 35% of randomly selected diabetes guideline recommendations use stronger causal language than the papers they cite. Such "causal jumps" are not necessarily unwarranted but, at best, lack of transparency in how causal conclusions were arrived at.
bmjopen.bmj.com
Causal language jumps and non-alignments between clinical practice guidelines and original studies: a systematic evaluation of diabetes guidelines and their cited evidence
Objectives Clinical practice guidelines are designed to guide clinical practice and often make causal claims when making recommendations. Sometimes, guidelines make or require stronger causal claims t...
1123
Reposted by Pausal Zivference
Pausal Zivference @pausalz.bsky.social · 02/02/2026
Last week I put out the v4.0 release of `delicatessen`, so I will summarize the new additions here
github.com
v4.0 by pzivich · Pull Request #67 · pzivich/Delicatessen
Major release Additions Display results via print_results() Display Results #80 Additional robust regression functions Additional Robust Functions #78 Beta regression model Finite-sample corre...
171
Pausal Zivference @pausalz.bsky.social · 02/02/2026
Last week I put out the v4.0 release of `delicatessen`, so I will summarize the new additions here
github.com
v4.0 by pzivich · Pull Request #67 · pzivich/Delicatessen
Major release Additions Display results via print_results() Display Results #80 Additional robust regression functions Additional Robust Functions #78 Beta regression model Finite-sample corre...
171
Pausal Zivference @pausalz.bsky.social · 29/01/2026
That K cliff looks like it drops off into the abyss
010
Reposted by Pausal Zivference
Tim Feeney @tfeend.bsky.social · 19/12/2025
As an editor I often see authors fall into a trap of stressing some fancy statistical technique for estimating causal effects. Often neglected are the necessary assumptions to map the data to the estimand. @pausalz.bsky.social and I wrote about it here www.bmj.com/content/391/... #EpiSky
bmj.com
Causal inference is hard, and advanced statistical analysis is not enough
Health researchers need to fully understand the underlying assumptions to uncover cause and effect. Timothy Feeney and Paul Zivich explain Physicians ask, answer, and interpret myriad causal question...
1156
Pausal Zivference @pausalz.bsky.social · 19/12/2025
As I am working on a major update to `delicatessen`, a catch-up #MEstimatorMonday (50/52) about a feature I am going to add Currently, I do not automatically handle non-independent data. v4.0 is likely to change this github.com/pzivich/Deli...
github.com
Handling Non-Independent Data · Issue #81 · pzivich/Delicatessen
Is your feature request related to a problem? Please describe. Right now (v3.2), there is not direct support for non-independent observations. Essentially, all one needs to do (with an independence...
170
Pausal Zivference @pausalz.bsky.social · 15/12/2025
This #MEstimatorMonday (49/52) let's look at beta regression. Beta regression is another regression model but for the case where the outcome Y is bounded (0,1) So, it is good for modeling proportions as outcomes. While we can also use fractional logistic regression, this is another option
120
Reposted by Pausal Zivference
Pausal Zivference @pausalz.bsky.social · 12/12/2025
I'm trying to find an example that was on Twitter back in 2021 to 2022 and hoping someone remembers better than me There was a very illustrative example of confounding by age for vaccination and COVID-19 outcomes. The vaccine looked harmful marginally, but was protective in each strata
104
Pausal Zivference @pausalz.bsky.social · 12/12/2025
I'm trying to find an example that was on Twitter back in 2021 to 2022 and hoping someone remembers better than me There was a very illustrative example of confounding by age for vaccination and COVID-19 outcomes. The vaccine looked harmful marginally, but was protective in each strata
104
Reposted by Pausal Zivference
Terry McGlynn @hormiga.bsky.social · 11/12/2025
You can do this right now: Think of a person who wrote a paper you love, whose work influenced or helped you, or has made your professional life better. Search up their email address. Shoot them a quick email of thanks. It means so, so much. This is a rough time of year, share some joy.
13699260
Pausal Zivference @pausalz.bsky.social · 09/12/2025
Since it's not actually Monday, I feel less guilty about this #MEstimatorMonday (48/52) which tells you how to do mediation analysis with estimating equations Let consider the effect of action A on outcome Y through mediator M
110
Pausal Zivference @pausalz.bsky.social · 08/12/2025
It's finals week, so let's space out on this #MEstimatorMonday (47/52). I've read a few astronomy books lately, so I was inspired to find an astrostatistics example with `delicatessen`. The following example models quasars deli.readthedocs.io/en/latest/Ex...
deli.readthedocs.io
Astrostatistics - Quasars — Delicatessen 3.2 documentation
220
Pausal Zivference @pausalz.bsky.social · 03/12/2025
This not-Monday #MEstimatorMonday (46/52) is to commemorate me finally getting around to finding an example of IV analysis from the econometric literature In other words, I found Wooldridge's book and the Mroz 1987 paper deli.readthedocs.io/en/latest/Ex...
deli.readthedocs.io
Mroz 1987: Regression and Instrumental Variables — Delicatessen 3.2 documentation
110
Pausal Zivference @pausalz.bsky.social · 02/12/2025
For the next catch-up-but-not-Monday #MEstimatorMonday (45/52) I am going to sketch out an argument I've been thinking about M-estimation, or the act of stacking estimating functions, has great potential to improve the statistical rigor of scientific research
150
Pausal Zivference @pausalz.bsky.social · 01/12/2025
For my final #MEstimatorMonday (44/52) of today, let's look at another confidence bands example This example ties in with #WorldAIDSDay as it relies on data from the AIDS Clinical Trial Group (ACTG) 175, comparing 2-drug versus 1-drug ART for prevention of disease progression among persons with HIV
111
Pausal Zivference @pausalz.bsky.social · 01/12/2025
For the 2nd #MEstimatorMonday (43/52) of today, let's look at those confidence bands a bit more. For this, I am going to reach outside my subject area and pontificate about cheminformatics
110
Pausal Zivference @pausalz.bsky.social · 01/12/2025
Turns out teaching really interferes with me staying on top of #MEstimatorMonday (42/52), so I need to do some catch up again To start, I am going to note a new release of `delicatessen` v3.2 The major addition of this release is confidence bands
140
Reposted by Pausal Zivference
Jeremy Labrecque @jeremylabrecque.bsky.social · 24/11/2025
What's it called when you're waiting for the bus and there are two different buses that could take you home? A doubly ro-busstop.
2142
Pausal Zivference @pausalz.bsky.social · 21/11/2025
Going to start referring to myself as a causalologist
061
Reposted by Pausal Zivference
Emily Moin @emilymoin.com · 19/11/2025
INCREDIBLE CURVES
1035778