Pan Zhao
@panzhao.bsky.social
Postdoctoral Research Associate, Statistical Laboratory, University of Cambridge
Reposted by Pan Zhao
Born #OnThisDay in 1867 was Marie Skłodowska–Curie, the first woman to win a Nobel Prize, the only woman to win twice and the only person to win a Nobel Prize in two disciplines: Physics for her work on radioactivity, and Chemistry for her discovery of radium and polonium. #WomenInSTEM
November 7, 2025 at 7:25 AM
Born #OnThisDay in 1867 was Marie Skłodowska–Curie, the first woman to win a Nobel Prize, the only woman to win twice and the only person to win a Nobel Prize in two disciplines: Physics for her work on radioactivity, and Chemistry for her discovery of radium and polonium. #WomenInSTEM
Reposted by Pan Zhao
Journal submissions got you stressed? Daniela Witten of the University of Washington shares advice about editing and dealing with rejection when submitting papers to academic journals. magazine.amstat.org/...
November 6, 2025 at 7:00 PM
Journal submissions got you stressed? Daniela Witten of the University of Washington shares advice about editing and dealing with rejection when submitting papers to academic journals. magazine.amstat.org/...
Reposted by Pan Zhao
Excellent report on experiences of @guidoimbens.bsky.social & Mary Wootters co-teaching "Causality, Decision Making, and Data Science" to undergrads at Stanford fall 2024: hdsr.mitpress.mit.edu/pub/uynpjlow... Course material here: stanford-causal-inference-class.github.io
November 3, 2025 at 4:14 PM
Excellent report on experiences of @guidoimbens.bsky.social & Mary Wootters co-teaching "Causality, Decision Making, and Data Science" to undergrads at Stanford fall 2024: hdsr.mitpress.mit.edu/pub/uynpjlow... Course material here: stanford-causal-inference-class.github.io
Reposted by Pan Zhao
Born #OnThisDay in 1815 was George Boole FRS. Boole was a mathematician, logician and philosopher who helped establish modern symbolic logic and whose algebra of logic, now called Boolean algebra, is fundamental to the design of digital computer circuits: https://bit.ly/3g1qY9c
November 2, 2025 at 1:53 PM
Born #OnThisDay in 1815 was George Boole FRS. Boole was a mathematician, logician and philosopher who helped establish modern symbolic logic and whose algebra of logic, now called Boolean algebra, is fundamental to the design of digital computer circuits: https://bit.ly/3g1qY9c
Reposted by Pan Zhao
Reposted by Pan Zhao
link 📈🤖
Prediction-Guided Active Experiments () arXiv:2411.12036v1 Announce Type: cross
Abstract: Here is the revised abstract, ensuring all characters are ASCII-compatible:
In this work, we introduce a new framework for active experimentation, the Prediction-Guided Active Experiment (PGAE), w
Prediction-Guided Active Experiments () arXiv:2411.12036v1 Announce Type: cross
Abstract: Here is the revised abstract, ensuring all characters are ASCII-compatible:
In this work, we introduce a new framework for active experimentation, the Prediction-Guided Active Experiment (PGAE), w
October 17, 2025 at 10:05 PM
link 📈🤖
Prediction-Guided Active Experiments () arXiv:2411.12036v1 Announce Type: cross
Abstract: Here is the revised abstract, ensuring all characters are ASCII-compatible:
In this work, we introduce a new framework for active experimentation, the Prediction-Guided Active Experiment (PGAE), w
Prediction-Guided Active Experiments () arXiv:2411.12036v1 Announce Type: cross
Abstract: Here is the revised abstract, ensuring all characters are ASCII-compatible:
In this work, we introduce a new framework for active experimentation, the Prediction-Guided Active Experiment (PGAE), w
Reposted by Pan Zhao
“All Our Default Models Are Wrong: Causal inference for varying treatment effects”: my talk this Saturday morning in Ottawa
statmodeling.stat.columbia.edu/2025/10/16/a...
statmodeling.stat.columbia.edu/2025/10/16/a...
“All Our Default Models Are Wrong: Causal inference for varying treatment effects”: my talk this Saturday morning in Ottawa | Statistical Modeling, Causal Inference, and Social Science
statmodeling.stat.columbia.edu
October 16, 2025 at 1:29 PM
“All Our Default Models Are Wrong: Causal inference for varying treatment effects”: my talk this Saturday morning in Ottawa
statmodeling.stat.columbia.edu/2025/10/16/a...
statmodeling.stat.columbia.edu/2025/10/16/a...
Reposted by Pan Zhao
For the 3rd day of my #MEstimatorMonday catch-up week (39/52), let's talk proximal causal inference
We can think about proximal causal inference as an extension of the standard identification assumptions to allow for more rich data structures. Specifically, we can account for unmeasured confounding
We can think about proximal causal inference as an extension of the standard identification assumptions to allow for more rich data structures. Specifically, we can account for unmeasured confounding
October 15, 2025 at 6:38 PM
For the 3rd day of my #MEstimatorMonday catch-up week (39/52), let's talk proximal causal inference
We can think about proximal causal inference as an extension of the standard identification assumptions to allow for more rich data structures. Specifically, we can account for unmeasured confounding
We can think about proximal causal inference as an extension of the standard identification assumptions to allow for more rich data structures. Specifically, we can account for unmeasured confounding
Reposted by Pan Zhao
Jane Goodall, world-renowned primatologist, dies aged 91
Jane Goodall, world-renowned primatologist, dies aged 91
Jane Goodall Institute says ‘tireless advocate’ for natural world died in California during US speaking tour
The world-renowned primatologist Jane Goodall has died at the age of 91, her institute has said.
The Jane Goodall Institute announced that she had passed away of natural causes while in California as part of a US speaking tour. Continue reading...
www.theguardian.com
October 1, 2025 at 6:35 PM
Jane Goodall, world-renowned primatologist, dies aged 91
Reposted by Pan Zhao
link 📈🤖
A note on the relation between one--step, outcome regression and IPW--type estimators of parameters with the mixed bias property (Rotnitzky, Smucler, Robins) Bruns-Smith et al. (2025) established an algebraic identity between the one-step estimator and a specific outcome regression-type e
A note on the relation between one--step, outcome regression and IPW--type estimators of parameters with the mixed bias property (Rotnitzky, Smucler, Robins) Bruns-Smith et al. (2025) established an algebraic identity between the one-step estimator and a specific outcome regression-type e
September 29, 2025 at 5:05 PM
link 📈🤖
A note on the relation between one--step, outcome regression and IPW--type estimators of parameters with the mixed bias property (Rotnitzky, Smucler, Robins) Bruns-Smith et al. (2025) established an algebraic identity between the one-step estimator and a specific outcome regression-type e
A note on the relation between one--step, outcome regression and IPW--type estimators of parameters with the mixed bias property (Rotnitzky, Smucler, Robins) Bruns-Smith et al. (2025) established an algebraic identity between the one-step estimator and a specific outcome regression-type e
Reposted by Pan Zhao
“Veridical (truthful) Data Science”: Another way of looking at statistical workflow
statmodeling.stat.columbia.edu/2025/09/28/v...
statmodeling.stat.columbia.edu/2025/09/28/v...
“Veridical (truthful) Data Science”: Another way of looking at statistical workflow | Statistical Modeling, Causal Inference, and Social Science
statmodeling.stat.columbia.edu
September 28, 2025 at 4:51 PM
“Veridical (truthful) Data Science”: Another way of looking at statistical workflow
statmodeling.stat.columbia.edu/2025/09/28/v...
statmodeling.stat.columbia.edu/2025/09/28/v...
Reposted by Pan Zhao
Excited to see our paper on evaluating whether AI can help humans make better decisions is now out in @pnas.org!
www.pnas.org/doi/10.1073/...
www.pnas.org/doi/10.1073/...
Does AI help humans make better decisions? A statistical evaluation framework for experimental and observational studies | PNAS
The use of AI, or more generally data-driven algorithms, has become ubiquitous in
today’s society. Yet, in many cases and especially when stakes ar...
www.pnas.org
September 25, 2025 at 2:41 AM
Excited to see our paper on evaluating whether AI can help humans make better decisions is now out in @pnas.org!
www.pnas.org/doi/10.1073/...
www.pnas.org/doi/10.1073/...
Reposted by Pan Zhao
Herbert P. Susmann, Alec McClean, Iv\'an D\'iaz
Non-overlap Average Treatment Effect Bounds
https://arxiv.org/abs/2509.20206
Non-overlap Average Treatment Effect Bounds
https://arxiv.org/abs/2509.20206
September 25, 2025 at 4:38 AM
Herbert P. Susmann, Alec McClean, Iv\'an D\'iaz
Non-overlap Average Treatment Effect Bounds
https://arxiv.org/abs/2509.20206
Non-overlap Average Treatment Effect Bounds
https://arxiv.org/abs/2509.20206
Reposted by Pan Zhao
NEW PAPER!!! "Causal Machine Learning Methods and Use of Cross‐Fitting in Settings With High‐Dimensional Confounding"
led by Susie Ellul, with Stijn Vansteelandt & John Carlin
Published in Stats in Med
Check it out 👇
onlinelibrary.wiley.com/doi/10.1002/...
#EpiSky #CausalSky
led by Susie Ellul, with Stijn Vansteelandt & John Carlin
Published in Stats in Med
Check it out 👇
onlinelibrary.wiley.com/doi/10.1002/...
#EpiSky #CausalSky
Causal Machine Learning Methods and Use of Cross‐Fitting in Settings With High‐Dimensional Confounding
Observational epidemiological studies commonly seek to estimate the causal effect of an exposure on an outcome. Adjustment for potential confounding bias in modern studies is challenging due to the p...
onlinelibrary.wiley.com
September 25, 2025 at 2:35 AM
NEW PAPER!!! "Causal Machine Learning Methods and Use of Cross‐Fitting in Settings With High‐Dimensional Confounding"
led by Susie Ellul, with Stijn Vansteelandt & John Carlin
Published in Stats in Med
Check it out 👇
onlinelibrary.wiley.com/doi/10.1002/...
#EpiSky #CausalSky
led by Susie Ellul, with Stijn Vansteelandt & John Carlin
Published in Stats in Med
Check it out 👇
onlinelibrary.wiley.com/doi/10.1002/...
#EpiSky #CausalSky
Reposted by Pan Zhao
New paper on generative modeling of counterfactual distributions! We give a way to answer "what if" questions with generative models.
For example: what would faces look like if they were all smiling?
arxiv.org/abs/2509.16842
For example: what would faces look like if they were all smiling?
arxiv.org/abs/2509.16842
September 24, 2025 at 8:42 PM
New paper on generative modeling of counterfactual distributions! We give a way to answer "what if" questions with generative models.
For example: what would faces look like if they were all smiling?
arxiv.org/abs/2509.16842
For example: what would faces look like if they were all smiling?
arxiv.org/abs/2509.16842
Reposted by Pan Zhao
link 📈🤖
DoubleGen: Debiased Generative Modeling of Counterfactuals (Luedtke, Fukumizu) Generative models for counterfactual outcomes face two key sources of bias. Confounding bias arises when approaches fail to account for systematic differences between those who receive the intervention and thos
DoubleGen: Debiased Generative Modeling of Counterfactuals (Luedtke, Fukumizu) Generative models for counterfactual outcomes face two key sources of bias. Confounding bias arises when approaches fail to account for systematic differences between those who receive the intervention and thos
September 23, 2025 at 7:33 PM
link 📈🤖
DoubleGen: Debiased Generative Modeling of Counterfactuals (Luedtke, Fukumizu) Generative models for counterfactual outcomes face two key sources of bias. Confounding bias arises when approaches fail to account for systematic differences between those who receive the intervention and thos
DoubleGen: Debiased Generative Modeling of Counterfactuals (Luedtke, Fukumizu) Generative models for counterfactual outcomes face two key sources of bias. Confounding bias arises when approaches fail to account for systematic differences between those who receive the intervention and thos
Reposted by Pan Zhao
link 📈🤖
Variable Selection for Additive Global Fr\'echet Regression (Yang, Bhattacharjee, Xue et al) We present a novel framework for variable selection in Fr\'echet regression with responses in general metric spaces, a setting increasingly relevant for analyzing non-Euclidean data such as probab
Variable Selection for Additive Global Fr\'echet Regression (Yang, Bhattacharjee, Xue et al) We present a novel framework for variable selection in Fr\'echet regression with responses in general metric spaces, a setting increasingly relevant for analyzing non-Euclidean data such as probab
September 18, 2025 at 4:39 PM
link 📈🤖
Variable Selection for Additive Global Fr\'echet Regression (Yang, Bhattacharjee, Xue et al) We present a novel framework for variable selection in Fr\'echet regression with responses in general metric spaces, a setting increasingly relevant for analyzing non-Euclidean data such as probab
Variable Selection for Additive Global Fr\'echet Regression (Yang, Bhattacharjee, Xue et al) We present a novel framework for variable selection in Fr\'echet regression with responses in general metric spaces, a setting increasingly relevant for analyzing non-Euclidean data such as probab
Reposted by Pan Zhao
Han Cui, Xinran Li
Robust Sensitivity Analysis via Augmented Percentile Bootstrap under Simultaneous Violations of Unconfoundedness and Overlap
https://arxiv.org/abs/2509.13169
Robust Sensitivity Analysis via Augmented Percentile Bootstrap under Simultaneous Violations of Unconfoundedness and Overlap
https://arxiv.org/abs/2509.13169
September 17, 2025 at 4:26 AM
Han Cui, Xinran Li
Robust Sensitivity Analysis via Augmented Percentile Bootstrap under Simultaneous Violations of Unconfoundedness and Overlap
https://arxiv.org/abs/2509.13169
Robust Sensitivity Analysis via Augmented Percentile Bootstrap under Simultaneous Violations of Unconfoundedness and Overlap
https://arxiv.org/abs/2509.13169
Reposted by Pan Zhao
Georgi Baklicharov, Kelly Van Lancker, Stijn Vansteelandt
Weakening assumptions in the evaluation of treatment effects in longitudinal randomized trials with truncation by death or other intercurrent events
https://arxiv.org/abs/2509.10067
Weakening assumptions in the evaluation of treatment effects in longitudinal randomized trials with truncation by death or other intercurrent events
https://arxiv.org/abs/2509.10067
September 15, 2025 at 5:03 AM
Georgi Baklicharov, Kelly Van Lancker, Stijn Vansteelandt
Weakening assumptions in the evaluation of treatment effects in longitudinal randomized trials with truncation by death or other intercurrent events
https://arxiv.org/abs/2509.10067
Weakening assumptions in the evaluation of treatment effects in longitudinal randomized trials with truncation by death or other intercurrent events
https://arxiv.org/abs/2509.10067
Reposted by Pan Zhao
Join #ENAR_ibs Friday, October 3 at 12 PM, when we host the #WebENAR "Sequential Causal Inference in Experimental or Observational Settings." More details at www.enar.org/education/in...
#causalinference #Biostatistics #statistics
#causalinference #Biostatistics #statistics
September 12, 2025 at 6:26 PM
Join #ENAR_ibs Friday, October 3 at 12 PM, when we host the #WebENAR "Sequential Causal Inference in Experimental or Observational Settings." More details at www.enar.org/education/in...
#causalinference #Biostatistics #statistics
#causalinference #Biostatistics #statistics
Reposted by Pan Zhao
The CAUSALab Methods Series @ki.se is back!
Fall 2025 lineup kicks off Sep 23 with Vanessa Didelez (BIPS), “Causal mediation and separable treatments in time-to-event analyses.”
All talks are virtual, except for Nov. 4, 2025 hybrid session.
Learn more & register:
hsph.harvard.edu/research/cau...
Fall 2025 lineup kicks off Sep 23 with Vanessa Didelez (BIPS), “Causal mediation and separable treatments in time-to-event analyses.”
All talks are virtual, except for Nov. 4, 2025 hybrid session.
Learn more & register:
hsph.harvard.edu/research/cau...
September 9, 2025 at 2:44 PM
The CAUSALab Methods Series @ki.se is back!
Fall 2025 lineup kicks off Sep 23 with Vanessa Didelez (BIPS), “Causal mediation and separable treatments in time-to-event analyses.”
All talks are virtual, except for Nov. 4, 2025 hybrid session.
Learn more & register:
hsph.harvard.edu/research/cau...
Fall 2025 lineup kicks off Sep 23 with Vanessa Didelez (BIPS), “Causal mediation and separable treatments in time-to-event analyses.”
All talks are virtual, except for Nov. 4, 2025 hybrid session.
Learn more & register:
hsph.harvard.edu/research/cau...
Reposted by Pan Zhao
link 📈🤖
Comment on "Deep Regression Learning with Optimal Loss Function" (Li) OpenReview benefits the peer-review system by promoting transparency, openness, and collaboration. By making reviews, comments, and author responses publicly accessible, the platform encourages constructive feedback, re
Comment on "Deep Regression Learning with Optimal Loss Function" (Li) OpenReview benefits the peer-review system by promoting transparency, openness, and collaboration. By making reviews, comments, and author responses publicly accessible, the platform encourages constructive feedback, re
September 5, 2025 at 4:06 PM
link 📈🤖
Comment on "Deep Regression Learning with Optimal Loss Function" (Li) OpenReview benefits the peer-review system by promoting transparency, openness, and collaboration. By making reviews, comments, and author responses publicly accessible, the platform encourages constructive feedback, re
Comment on "Deep Regression Learning with Optimal Loss Function" (Li) OpenReview benefits the peer-review system by promoting transparency, openness, and collaboration. By making reviews, comments, and author responses publicly accessible, the platform encourages constructive feedback, re
Reposted by Pan Zhao
link 📈🤖
Confounder selection via iterative graph expansion (Guo, Zhao) Confounder selection, namely choosing a set of covariates to control for confounding between a treatment and an outcome, is arguably the most important step in the design of an observational study. Previous methods, such as Pe
Confounder selection via iterative graph expansion (Guo, Zhao) Confounder selection, namely choosing a set of covariates to control for confounding between a treatment and an outcome, is arguably the most important step in the design of an observational study. Previous methods, such as Pe
September 4, 2025 at 11:03 PM
link 📈🤖
Confounder selection via iterative graph expansion (Guo, Zhao) Confounder selection, namely choosing a set of covariates to control for confounding between a treatment and an outcome, is arguably the most important step in the design of an observational study. Previous methods, such as Pe
Confounder selection via iterative graph expansion (Guo, Zhao) Confounder selection, namely choosing a set of covariates to control for confounding between a treatment and an outcome, is arguably the most important step in the design of an observational study. Previous methods, such as Pe
Reposted by Pan Zhao
link 📈🤖
Evaluation of Surrogate Endpoints Based on Meta-Analysis with Surrogate Indices (Stijven, Gilbert) We introduce in this paper an extension of the meta-analytic (MA) framework for evaluating surrogate endpoints. While the MA framework is regarded as the gold standard for surrogate endpoint
Evaluation of Surrogate Endpoints Based on Meta-Analysis with Surrogate Indices (Stijven, Gilbert) We introduce in this paper an extension of the meta-analytic (MA) framework for evaluating surrogate endpoints. While the MA framework is regarded as the gold standard for surrogate endpoint
September 3, 2025 at 5:34 PM
link 📈🤖
Evaluation of Surrogate Endpoints Based on Meta-Analysis with Surrogate Indices (Stijven, Gilbert) We introduce in this paper an extension of the meta-analytic (MA) framework for evaluating surrogate endpoints. While the MA framework is regarded as the gold standard for surrogate endpoint
Evaluation of Surrogate Endpoints Based on Meta-Analysis with Surrogate Indices (Stijven, Gilbert) We introduce in this paper an extension of the meta-analytic (MA) framework for evaluating surrogate endpoints. While the MA framework is regarded as the gold standard for surrogate endpoint
Reposted by Pan Zhao
An announcement, which might be of some interest:
In the period 2022-2024, myself and a number of other postdocs on the "CoSInES" and "Bayes4Health" EPSRC grants were involved in organising a number of internal tutorial workshops, on topics relevant to researchers in computational statistics.
In the period 2022-2024, myself and a number of other postdocs on the "CoSInES" and "Bayes4Health" EPSRC grants were involved in organising a number of internal tutorial workshops, on topics relevant to researchers in computational statistics.
September 2, 2025 at 12:13 PM
An announcement, which might be of some interest:
In the period 2022-2024, myself and a number of other postdocs on the "CoSInES" and "Bayes4Health" EPSRC grants were involved in organising a number of internal tutorial workshops, on topics relevant to researchers in computational statistics.
In the period 2022-2024, myself and a number of other postdocs on the "CoSInES" and "Bayes4Health" EPSRC grants were involved in organising a number of internal tutorial workshops, on topics relevant to researchers in computational statistics.