Posts by Tags
CausalInference
Experiments
The Culture of Causal Inference: From Theory to Practice: A ⟶ B
Foundations of Causal Inference
MachineLearning
The Culture of Causal Inference: From Theory to Practice: A ⟶ B
Foundations of Causal Inference
Uber
The Culture of Causal Inference: From Theory to Practice: A ⟶ B
Foundations of Causal Inference
behairal economics
Список для чтения по поведенческой и экспериментальной экономике
5 лет назад совместно с «Всероссийской государственной библиотекой иностранной литературы имени М.И.Рудомино» я сделал рекомендательный список литературы и периодики, посвященных поведенческой экономике. Публикую его сегодня, следуя рекомендации, когда-то данной мне Быковским – спустя 5 лет, и сопровождая сегодняшними комментариями.
category1
Future Blog Post
This post will show up by default. To disable scheduling of future posts, edit config.yml
and set future: false
.
category2
Future Blog Post
This post will show up by default. To disable scheduling of future posts, edit config.yml
and set future: false
.
causal-ml-book
Review of Chernozhukov’s Causal ML Textbook
On Twitter/X, there’s been a lot of discussion about Chernozhukov’s textbook, which came out on February 24th. Having read several chapters in detail and skimmed through the rest, here’s my take on it.
causality
The Culture of Causal Inference: From Theory to Practice: A ⟶ B
Foundations of Causal Inference
Fresh Example of Simpson’s Paradox in Clinical Trials
A fresh example of Simpson’s Paradox in the wild has recently emerged! Here’s the story: some researchers and policymakers argue that the NIH (National Institutes of Health) funds too many “small and crappy” trials, which has been regularly reported in the press.
Review of Chernozhukov’s Causal ML Textbook
On Twitter/X, there’s been a lot of discussion about Chernozhukov’s textbook, which came out on February 24th. Having read several chapters in detail and skimmed through the rest, here’s my take on it.
Alternative Approach to Causal Libraries
Having recently done a review of libraries on causality, I have the impression that Microsoft’s option is the most viable among others, since it has technical support, promotion and community support. However, I am not mostly a big fan of this “specify all the parameters you can and step aside” approach.
Trends from the Third Annual Causal Data Science Meeting
Not so long ago, the third annual Causal Data Science Meeting was held on November 7-8. Among the trends this year, it is worth noting that, unlike in previous years, there are more and more papers on methods directly working in or being developed for production environments.
List of Causal Libraries
Name | Team | Software | Keywords | link |
causalai | Salesforce | Python | Discovery | Time Series | basic-inference | https://github.com/salesforce/causalai |
pycid | Causal Incentives Working Group a collaboration with Oxford, DeepMind and Toronto researchers | Python | bayesian-networks | influence-diagrams | https://github.com/causalincentives/pycid |
causal-learn | Center for Causal Discovery, pittsbugh | Python | discovery |hidden-causal | Time Series basic-inference | tetrad | https://github.com/causalincentives/pycid |
CausalImpact | Google, Inc | R | Bayesian time-series | https://github.com/google/CausalImpact |
EconML | Microsoft Research | Python | Machine Learning Based Estimation of Heterogeneous Treatment Effects | https://econml.azurewebsites.net/index.html |
causalnex | Petuum | Python | augment model | structure learning | https://causalnex.readthedocs.io/en/latest/index.html |
dowhy | Microsoft Research | Python | Double ML | Matching | Balancing Synthetic control Outcome-based Learners (e.f. X-Learner) Dif&Dif | basic-inference | https://github.com/py-why/dowhy |
causalToolbox | University of California | R | X-learner | https://github.com/forestry-labs/causalToolbox |
showwhy | Microsoft Research | TypeScript | no-code interfaces | https://github.com/microsoft/showwhy |
causalimages-software | The University of Texas at Austin | R | computer-vision | earth-observation biomedical-image-analysis | https://github.com/cjerzak/causalimages-software |
gCastle | Huawei Noah's Ark Lab | Python | Structure Learning gradient-based learning | https://github.com/huawei-noah/trustworthyAI/tree/master/gcastle |
causallib | BiomedSciAI | Python | basic-inference | https://github.com/BiomedSciAI/causallib |
causal-cmd | Center for Causal Discovery, pittsbugh | java | CMD based | discovery | https://bd2kccd.github.io/docs/causal-cmd/ |
ResearchMap | UCLA | JS | Optimal experiments | augmented models | https://github.com/ResearchMaps/ |
Список для чтения по поведенческой и экспериментальной экономике
5 лет назад совместно с «Всероссийской государственной библиотекой иностранной литературы имени М.И.Рудомино» я сделал рекомендательный список литературы и периодики, посвященных поведенческой экономике. Публикую его сегодня, следуя рекомендации, когда-то данной мне Быковским – спустя 5 лет, и сопровождая сегодняшними комментариями.
conferences
Trends from the Third Annual Causal Data Science Meeting
Not so long ago, the third annual Causal Data Science Meeting was held on November 7-8. Among the trends this year, it is worth noting that, unlike in previous years, there are more and more papers on methods directly working in or being developed for production environments.
cool posts
Future Blog Post
This post will show up by default. To disable scheduling of future posts, edit config.yml
and set future: false
.
data science
The Culture of Causal Inference: From Theory to Practice: A ⟶ B
Foundations of Causal Inference
Trends from the Third Annual Causal Data Science Meeting
Not so long ago, the third annual Causal Data Science Meeting was held on November 7-8. Among the trends this year, it is worth noting that, unlike in previous years, there are more and more papers on methods directly working in or being developed for production environments.
effectiveness
eng
The Culture of Causal Inference: From Theory to Practice: A ⟶ B
Foundations of Causal Inference
Fresh Example of Simpson’s Paradox in Clinical Trials
A fresh example of Simpson’s Paradox in the wild has recently emerged! Here’s the story: some researchers and policymakers argue that the NIH (National Institutes of Health) funds too many “small and crappy” trials, which has been regularly reported in the press.
Review of Chernozhukov’s Causal ML Textbook
On Twitter/X, there’s been a lot of discussion about Chernozhukov’s textbook, which came out on February 24th. Having read several chapters in detail and skimmed through the rest, here’s my take on it.
Alternative Approach to Causal Libraries
Having recently done a review of libraries on causality, I have the impression that Microsoft’s option is the most viable among others, since it has technical support, promotion and community support. However, I am not mostly a big fan of this “specify all the parameters you can and step aside” approach.
Trends from the Third Annual Causal Data Science Meeting
Not so long ago, the third annual Causal Data Science Meeting was held on November 7-8. Among the trends this year, it is worth noting that, unlike in previous years, there are more and more papers on methods directly working in or being developed for production environments.
List of Causal Libraries
Name | Team | Software | Keywords | link |
causalai | Salesforce | Python | Discovery | Time Series | basic-inference | https://github.com/salesforce/causalai |
pycid | Causal Incentives Working Group a collaboration with Oxford, DeepMind and Toronto researchers | Python | bayesian-networks | influence-diagrams | https://github.com/causalincentives/pycid |
causal-learn | Center for Causal Discovery, pittsbugh | Python | discovery |hidden-causal | Time Series basic-inference | tetrad | https://github.com/causalincentives/pycid |
CausalImpact | Google, Inc | R | Bayesian time-series | https://github.com/google/CausalImpact |
EconML | Microsoft Research | Python | Machine Learning Based Estimation of Heterogeneous Treatment Effects | https://econml.azurewebsites.net/index.html |
causalnex | Petuum | Python | augment model | structure learning | https://causalnex.readthedocs.io/en/latest/index.html |
dowhy | Microsoft Research | Python | Double ML | Matching | Balancing Synthetic control Outcome-based Learners (e.f. X-Learner) Dif&Dif | basic-inference | https://github.com/py-why/dowhy |
causalToolbox | University of California | R | X-learner | https://github.com/forestry-labs/causalToolbox |
showwhy | Microsoft Research | TypeScript | no-code interfaces | https://github.com/microsoft/showwhy |
causalimages-software | The University of Texas at Austin | R | computer-vision | earth-observation biomedical-image-analysis | https://github.com/cjerzak/causalimages-software |
gCastle | Huawei Noah's Ark Lab | Python | Structure Learning gradient-based learning | https://github.com/huawei-noah/trustworthyAI/tree/master/gcastle |
causallib | BiomedSciAI | Python | basic-inference | https://github.com/BiomedSciAI/causallib |
causal-cmd | Center for Causal Discovery, pittsbugh | java | CMD based | discovery | https://bd2kccd.github.io/docs/causal-cmd/ |
ResearchMap | UCLA | JS | Optimal experiments | augmented models | https://github.com/ResearchMaps/ |
experiments
Список для чтения по поведенческой и экспериментальной экономике
5 лет назад совместно с «Всероссийской государственной библиотекой иностранной литературы имени М.И.Рудомино» я сделал рекомендательный список литературы и периодики, посвященных поведенческой экономике. Публикую его сегодня, следуя рекомендации, когда-то данной мне Быковским – спустя 5 лет, и сопровождая сегодняшними комментариями.
libraries
Alternative Approach to Causal Libraries
Having recently done a review of libraries on causality, I have the impression that Microsoft’s option is the most viable among others, since it has technical support, promotion and community support. However, I am not mostly a big fan of this “specify all the parameters you can and step aside” approach.
lists
List of Causal Libraries
Name | Team | Software | Keywords | link |
causalai | Salesforce | Python | Discovery | Time Series | basic-inference | https://github.com/salesforce/causalai |
pycid | Causal Incentives Working Group a collaboration with Oxford, DeepMind and Toronto researchers | Python | bayesian-networks | influence-diagrams | https://github.com/causalincentives/pycid |
causal-learn | Center for Causal Discovery, pittsbugh | Python | discovery |hidden-causal | Time Series basic-inference | tetrad | https://github.com/causalincentives/pycid |
CausalImpact | Google, Inc | R | Bayesian time-series | https://github.com/google/CausalImpact |
EconML | Microsoft Research | Python | Machine Learning Based Estimation of Heterogeneous Treatment Effects | https://econml.azurewebsites.net/index.html |
causalnex | Petuum | Python | augment model | structure learning | https://causalnex.readthedocs.io/en/latest/index.html |
dowhy | Microsoft Research | Python | Double ML | Matching | Balancing Synthetic control Outcome-based Learners (e.f. X-Learner) Dif&Dif | basic-inference | https://github.com/py-why/dowhy |
causalToolbox | University of California | R | X-learner | https://github.com/forestry-labs/causalToolbox |
showwhy | Microsoft Research | TypeScript | no-code interfaces | https://github.com/microsoft/showwhy |
causalimages-software | The University of Texas at Austin | R | computer-vision | earth-observation biomedical-image-analysis | https://github.com/cjerzak/causalimages-software |
gCastle | Huawei Noah's Ark Lab | Python | Structure Learning gradient-based learning | https://github.com/huawei-noah/trustworthyAI/tree/master/gcastle |
causallib | BiomedSciAI | Python | basic-inference | https://github.com/BiomedSciAI/causallib |
causal-cmd | Center for Causal Discovery, pittsbugh | java | CMD based | discovery | https://bd2kccd.github.io/docs/causal-cmd/ |
ResearchMap | UCLA | JS | Optimal experiments | augmented models | https://github.com/ResearchMaps/ |
rus
Список для чтения по поведенческой и экспериментальной экономике
5 лет назад совместно с «Всероссийской государственной библиотекой иностранной литературы имени М.И.Рудомино» я сделал рекомендательный список литературы и периодики, посвященных поведенческой экономике. Публикую его сегодня, следуя рекомендации, когда-то данной мне Быковским – спустя 5 лет, и сопровождая сегодняшними комментариями.
simpson-paradox
Fresh Example of Simpson’s Paradox in Clinical Trials
A fresh example of Simpson’s Paradox in the wild has recently emerged! Here’s the story: some researchers and policymakers argue that the NIH (National Institutes of Health) funds too many “small and crappy” trials, which has been regularly reported in the press.
software
Alternative Approach to Causal Libraries
Having recently done a review of libraries on causality, I have the impression that Microsoft’s option is the most viable among others, since it has technical support, promotion and community support. However, I am not mostly a big fan of this “specify all the parameters you can and step aside” approach.
List of Causal Libraries
Name | Team | Software | Keywords | link |
causalai | Salesforce | Python | Discovery | Time Series | basic-inference | https://github.com/salesforce/causalai |
pycid | Causal Incentives Working Group a collaboration with Oxford, DeepMind and Toronto researchers | Python | bayesian-networks | influence-diagrams | https://github.com/causalincentives/pycid |
causal-learn | Center for Causal Discovery, pittsbugh | Python | discovery |hidden-causal | Time Series basic-inference | tetrad | https://github.com/causalincentives/pycid |
CausalImpact | Google, Inc | R | Bayesian time-series | https://github.com/google/CausalImpact |
EconML | Microsoft Research | Python | Machine Learning Based Estimation of Heterogeneous Treatment Effects | https://econml.azurewebsites.net/index.html |
causalnex | Petuum | Python | augment model | structure learning | https://causalnex.readthedocs.io/en/latest/index.html |
dowhy | Microsoft Research | Python | Double ML | Matching | Balancing Synthetic control Outcome-based Learners (e.f. X-Learner) Dif&Dif | basic-inference | https://github.com/py-why/dowhy |
causalToolbox | University of California | R | X-learner | https://github.com/forestry-labs/causalToolbox |
showwhy | Microsoft Research | TypeScript | no-code interfaces | https://github.com/microsoft/showwhy |
causalimages-software | The University of Texas at Austin | R | computer-vision | earth-observation biomedical-image-analysis | https://github.com/cjerzak/causalimages-software |
gCastle | Huawei Noah's Ark Lab | Python | Structure Learning gradient-based learning | https://github.com/huawei-noah/trustworthyAI/tree/master/gcastle |
causallib | BiomedSciAI | Python | basic-inference | https://github.com/BiomedSciAI/causallib |
causal-cmd | Center for Causal Discovery, pittsbugh | java | CMD based | discovery | https://bd2kccd.github.io/docs/causal-cmd/ |
ResearchMap | UCLA | JS | Optimal experiments | augmented models | https://github.com/ResearchMaps/ |
statistics
Fresh Example of Simpson’s Paradox in Clinical Trials
A fresh example of Simpson’s Paradox in the wild has recently emerged! Here’s the story: some researchers and policymakers argue that the NIH (National Institutes of Health) funds too many “small and crappy” trials, which has been regularly reported in the press.
teamwork
textbooks
Review of Chernozhukov’s Causal ML Textbook
On Twitter/X, there’s been a lot of discussion about Chernozhukov’s textbook, which came out on February 24th. Having read several chapters in detail and skimmed through the rest, here’s my take on it.