Sherri Rose
@sherrirose.bsky.social
Stanford Professor | Computational Health Economics & Outcomes | Fair Machine Learning | Causality | Statistics | Health Policy | Health Equity
drsherrirose.org
Lab manual: stanfordhpds.github.io/lab_manual
Personal account
drsherrirose.org
Lab manual: stanfordhpds.github.io/lab_manual
Personal account
The repo is still private. (My custom theme needs work. 🙃) Will share a public release!
January 9, 2025 at 3:57 AM
The repo is still private. (My custom theme needs work. 🙃) Will share a public release!
Clarification: these were entirely different major projects published in stats, econ, and clinical journals. No LPUs! Then synthesized together in a policy brief.
January 9, 2025 at 3:55 AM
Clarification: these were entirely different major projects published in stats, econ, and clinical journals. No LPUs! Then synthesized together in a policy brief.
Great summaries, thanks!!
January 9, 2025 at 3:54 AM
Great summaries, thanks!!
Right?? Great build. Also very cute.
December 28, 2024 at 10:54 PM
Right?? Great build. Also very cute.
Indeed. Many successful academics are miserable because they are always trying to accumulate more high-profile successes. There is no enough.
December 27, 2024 at 11:35 PM
Indeed. Many successful academics are miserable because they are always trying to accumulate more high-profile successes. There is no enough.
sorry but if we mention weather you know I have to do this. Stanford in December…
December 23, 2024 at 8:35 PM
sorry but if we mention weather you know I have to do this. Stanford in December…
Reposted by Sherri Rose
tl;dr Healthcare access disparities cascade through the entire ML pipeline.
Check out our working paper here: arxiv.org/pdf/2412.07712
Check out our working paper here: arxiv.org/pdf/2412.07712
December 20, 2024 at 1:04 AM
tl;dr Healthcare access disparities cascade through the entire ML pipeline.
Check out our working paper here: arxiv.org/pdf/2412.07712
Check out our working paper here: arxiv.org/pdf/2412.07712
We also examined identifying intersectional groups defined by multiple health conditions here: informatics.bmj.com/content/28/1...
Identifying undercompensated groups defined by multiple attributes in risk adjustment
Objective To identify undercompensated groups in plan payment risk adjustment that are defined by multiple attributes with a systematic new approach, improving on the arbitrary and inconsistent nature...
informatics.bmj.com
December 15, 2024 at 8:52 PM
We also examined identifying intersectional groups defined by multiple health conditions here: informatics.bmj.com/content/28/1...
You may have already seen these, but we looked at comorbidities here, using constraints for multiple health conditions, which improved fairness metrics for 88% of other undercompensated conditions that weren't included as constraints: www.journals.uchicago.edu/doi/10.1086/...
Improving the Performance of Risk Adjustment Systems : Constrained Regressions, Reinsurance, and Variable Selection | American Journal of Health Economics: Vol 7, No 4
Abstract Modifications of risk adjustment systems used to pay health plans in individual health insurance markets typically seek to reduce selection incentives at the individual and group levels by ad...
www.journals.uchicago.edu
December 15, 2024 at 8:51 PM
You may have already seen these, but we looked at comorbidities here, using constraints for multiple health conditions, which improved fairness metrics for 88% of other undercompensated conditions that weren't included as constraints: www.journals.uchicago.edu/doi/10.1086/...
Here's a link to the 1st 4 chapters from our 2nd targeted learning book, which handles time-varying covs, w/longitudinal TMLE in Ch 4: drsherrirose.org/s/Ch1to4_TLB.... There are also tutorials on LTMLE (e.g., onlinelibrary.wiley.com/doi/10.1002/...) & R package: cran.r-project.org/web/packages....
December 10, 2024 at 3:52 AM
Here's a link to the 1st 4 chapters from our 2nd targeted learning book, which handles time-varying covs, w/longitudinal TMLE in Ch 4: drsherrirose.org/s/Ch1to4_TLB.... There are also tutorials on LTMLE (e.g., onlinelibrary.wiley.com/doi/10.1002/...) & R package: cran.r-project.org/web/packages....
also recommendation letters 🙃
November 29, 2024 at 10:29 PM
also recommendation letters 🙃
A few more! @guidoimbens.bsky.social @jugander.bsky.social @jsalomon.bsky.social @maya-rossin-slater.bsky.social @susanathey.bsky.social @russpoldrack.bsky.social
November 24, 2024 at 7:54 PM
Interested in all broad feedback. 🙂 We discuss barriers to uptake in the course and potential solutions. I wanted to hear about current challenges people face to incorporate additional issues. Every organization, field, etc has different barriers.
November 22, 2024 at 6:41 PM
Interested in all broad feedback. 🙂 We discuss barriers to uptake in the course and potential solutions. I wanted to hear about current challenges people face to incorporate additional issues. Every organization, field, etc has different barriers.
Collaborative writing is indeed a challenge when not everyone uses the same ecosystem. We currently use quarto, but not all collaborators do. So this might involve exporting a word file and merging those comments back into the .qmd. Not a seamless solution, but better than some others we've used.
November 22, 2024 at 6:36 PM
Collaborative writing is indeed a challenge when not everyone uses the same ecosystem. We currently use quarto, but not all collaborators do. So this might involve exporting a word file and merging those comments back into the .qmd. Not a seamless solution, but better than some others we've used.