Douglas J. McCallan
@measurementerror.bsky.social
Dwight Schrute's hidden brother, mostly interested in casual inference, drums and beets
Reposted by Douglas J. McCallan
The code to follow step-by-step is available here: github.com/paulgp/GPHK_...
The paper is here: arxiv.org/pdf/2511.03572
The UJIVE package is here: github.com/kolesarm/Man...
The paper is here: arxiv.org/pdf/2511.03572
The UJIVE package is here: github.com/kolesarm/Man...
GitHub - paulgp/GPHK_JEP_Replication_Package
Contribute to paulgp/GPHK_JEP_Replication_Package development by creating an account on GitHub.
github.com
November 17, 2025 at 3:06 PM
The code to follow step-by-step is available here: github.com/paulgp/GPHK_...
The paper is here: arxiv.org/pdf/2511.03572
The UJIVE package is here: github.com/kolesarm/Man...
The paper is here: arxiv.org/pdf/2511.03572
The UJIVE package is here: github.com/kolesarm/Man...
Reposted by Douglas J. McCallan
Thanks everyone for the replies!
Some links for future me: this awesome list curated by Nick Huntington Klein
www.goodreads.com/review/list/...
And this thread
bsky.app/profile/just...
Some links for future me: this awesome list curated by Nick Huntington Klein
www.goodreads.com/review/list/...
And this thread
bsky.app/profile/just...
July 6, 2025 at 7:05 AM
Thanks everyone for the replies!
Some links for future me: this awesome list curated by Nick Huntington Klein
www.goodreads.com/review/list/...
And this thread
bsky.app/profile/just...
Some links for future me: this awesome list curated by Nick Huntington Klein
www.goodreads.com/review/list/...
And this thread
bsky.app/profile/just...
Reposted by Douglas J. McCallan
yes, but I would say it's good practice to first try the fully interacted model (or equivalently the split sample) before just to be sure.
This paper makes a very good case for it direct.mit.edu/rest/article...
This paper makes a very good case for it direct.mit.edu/rest/article...
Omitted Variable Bias in Interacted Models: A Cautionary Tale
Abstract. We highlight that analyses using interaction terms to study treatment effect heterogeneity are susceptible to a form of omitted variable bias that is often overlooked in economics. Unlike mo...
direct.mit.edu
May 9, 2025 at 4:27 PM
yes, but I would say it's good practice to first try the fully interacted model (or equivalently the split sample) before just to be sure.
This paper makes a very good case for it direct.mit.edu/rest/article...
This paper makes a very good case for it direct.mit.edu/rest/article...
Reposted by Douglas J. McCallan
Here's a couple impressive studies using solar panel suitability and visibility to others
pubmed.ncbi.nlm.nih.gov/30356217/
doi.org/10.1287/mksc...
pubmed.ncbi.nlm.nih.gov/30356217/
doi.org/10.1287/mksc...
Visibility and Peer Influence in Durable Good Adoption | Marketing Science
doi.org
February 15, 2025 at 10:35 PM
Here's a couple impressive studies using solar panel suitability and visibility to others
pubmed.ncbi.nlm.nih.gov/30356217/
doi.org/10.1287/mksc...
pubmed.ncbi.nlm.nih.gov/30356217/
doi.org/10.1287/mksc...
Reposted by Douglas J. McCallan
@maxkasy.bsky.social uses POs in his bandit and reinforcement learning slides here maxkasy.github.io/home/ML_Oxfo...
Foundations of Machine Learning
Research on machine learning, experimental design, economic inequality, and optimal policy
maxkasy.github.io
January 16, 2025 at 8:47 AM
@maxkasy.bsky.social uses POs in his bandit and reinforcement learning slides here maxkasy.github.io/home/ML_Oxfo...