Calculating Confidence Intervals for Impact Numbers
Author Information
Author(s): Hildebrandt Mandy, Bender Ralf, Gehrmann Ulrich, Blettner Maria
Primary Institution: Institute for Quality and Efficiency in Health Care (IQWiG)
Hypothesis
How can confidence intervals be calculated for new epidemiological effect measures called impact numbers?
Conclusion
Calculating confidence intervals for impact numbers provides additional information and helps interpret study results in public health research.
Supporting Evidence
- The study calculated impact numbers for smoking-related deaths from coronary heart disease and stroke.
- The confidence intervals for the case impact number (CIN) and exposed cases impact number (ECIN) were calculated.
- The methods presented can be applied to other epidemiological studies.
Takeaway
This study shows how to calculate confidence intervals for new numbers that help us understand the impact of things like smoking on health.
Methodology
The study presents methods to calculate confidence intervals for impact numbers based on known methods for attributable risk measures.
Limitations
The study assumes no confounders and fixed follow-up times, which may not be applicable in all real-world scenarios.
Participant Demographics
The study analyzed data from British and Japanese cohorts, including male doctors and middle-aged men and women.
Statistical Information
Confidence Interval
[3.84, 20.36]
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website