Welcome to our space about sensitivity analysis.
Questions? Issues? Suggestions? Reach out through the KounFound-It! Google Group.
Purpose
All of the assumptions of statistical analysis rarely hold. So the challenge for the pragmatist is to understand when evidence is strong enough to support action. That’s where sensitivity analysis comes in—so we can understand how robust our inferences are to challenges to our assumptions. One example is a statement such as:
XX% of the estimated effect would have to be due to bias to change your inference about the effect.
But that’s just one. In this website, we discuss lots of approaches, applications, and the pluses and minuses.
Our work in the KonFound-It project is to develop—and make easy to use—sensitivity analyses that quantify the robustness of inferences to concerns about omitted variables and other sources of bias.
People
We are a group of researchers spanning numerous institutions who would like to contribute to better communications of research inferences and findings.
Our group includes:
- Ken Frank (Michigan State University)
- Spiro Maroulis (Arizona State University)
- Qinyun Lin (University of Gothenburg)
- Ran Xu (University of Connecticut)
- Joshua Rosenberg (University of Tennessee, Knoxville)
- Guan Saw (Claremont Graduate University)
- Bret Staudt Willet (Florida State University)
Additional contributors include:
- Tingqiao Chen (Michigan State University)
- Zixi Chen (NYU Shanghai)
- Xuesen Cheng (Michigan State University)
- Jihoon Choi (Michigan State University)
- Tenglong Li (Xi’an Jiaotong-Liverpool University)
- Yuqing Liu (Michigan State University)
- Dallin Overstreet (Arizona State University)
- Wei Pan (Duke University)
- Wei Wang (Michigan State University)
- Gaofei Zhang (University of Connecticut)
Tools
KonFound-It! Shiny App
Rosenberg, J. M., Narvaiz, S., Xu, R., Lin, Q., Maroulis, S., Frank, K. A., Saw, G. & Staudt Willet, K. B. (2023). KonFound-it!: Quantify the robustness of causal inferences (v. 2.0.0). https://konfound-project.shinyapps.io/konfound-it/
KonFound R Package
Rosenberg, J. M., Xu, R., Lin, Q., Maroulis, S., & Frank, K. A. (2023). konfound: Quantify the robustness of causal inferences (v. 0.4.0). https://CRAN.R-project.org/package=konfound
| Monthly Downloads | Total Downloads |
|---|---|
- Development version of the R package: KonFound Project on GitHub
- Narvaiz, S., Lin, Q., Rosenberg, J. M., Frank, K. A., Maroulis, S. J., Wang, W., & Xu, R. (2024). konfound: An R sensitivity analysis package to quantify the robustness of causal inferences. Journal of Open Source Software, 9(95), 5779. Web
install.packages("konfound")
library(konfound)
pkonfound(est_eff = -9.01, std_err = .68, n_obs = 7639, n_covariates = 221)
KonFound Stata Package
Xu, R., Frank, K. A., Maroulis, S. J., & Rosenberg, J. M. (2019). konfound: Command to quantify robustness of causal inferences. The Stata Journal, 19(3), 523-550. https://doi.org/10.1177/1536867X19874223
ssc install konfound
ssc install indeplist
ssc install moss
ssc install matsort
pkonfound -9.01 .68 7639 221
Benchmarks: What Works Clearinghouse
COMING SOON
Internal Resources
Be sure to look through the variety of supports for KonFound:
- Forum (Google Group)
- FAQ | FAQ Dev Version
- Resource Overview
- Publications
- Talks
- Workshops
- User Guide - COMING SOON
- Benchmarks: What Works Clearinghouse - COMING SOON
External Resources
We refer to a lot of open resources for building this site, including:
Connect
- Project Overview and Details: Peruse the KonFound-It! Website
- Frequently Asked Questions: Check the FAQ page | FAQ dev version
- Specific Questions: Ask in the KounFound-It! Google Group
- Issues with the konfound R Package: Post to konfound GitHub Issues
- Overall KonFound-It! Project Inquiries: Contact Ken Frank
- Benchmarks: What Works Clearinghouse: Contact Spiro Maroulis
- R Package: Contact Qinyun Lin
- R Shiny App: Contact Joshua Rosenberg
- Stata Package: Contact Ran Xu
- User Guide: Contact Guan Saw
- Website: Contact Bret Staudt Willet