Title
A calibration approach to transportability with observational data
What is this about?
Methods that address confounding and enhance transportability of study results across populations are essential for internally and externally valid causal inference, respectively. The authors develop a weighting method which estimates the effect of an intervention on an outcome in an observational study which can then be transported to a second, possibly unrelated target population.
Type
Original research
Year
2020
Domain
causal_inference
Authors
Josey KP, Yang F, Ghosh D, Raghavan S
Reference
arXiv:2008.06615v1 [stat.ME]
Keywords
Transportability; observational studies; generalizability; external validity; confounding; sampling weights; calibration; data-fusion
Comments
Not peer-reviewed
Open access
Yes
Code
Yes
Lifecycle Tutorial
No