Correcting Weight Reporting in National Health Interview Survey
Author Information
Author(s): Eric N Reither, Rebecca L Utz
Primary Institution: Utah State University
Hypothesis
The unusually large increase in mean BMI between 1996 and 1997 is primarily attributable to methodological changes in the NHIS.
Conclusion
The correction procedure developed in this study significantly improves the quality of BMI estimates in the NHIS by addressing biases introduced by proxy-reporting.
Supporting Evidence
- Proxy-reports of weight tended to be biased downward.
- The correction procedure minimized BMI underestimation associated with proxy-reporting.
- Mean BMI from proxy-reports was generally lower than from self-reports.
- Biases in reporting varied by race and sex.
- Significant interactions were found between reporting status and sociodemographic variables.
Takeaway
This study shows that when people report their weight through someone else, it can be wrong, and we created a way to fix those mistakes to get better health information.
Methodology
Merged NHIS data from 1976–2002 and developed a correction procedure for biases in BMI due to reporting status.
Potential Biases
Potential biases in proxy-reported data may vary by race, sex, and socioeconomic status.
Limitations
The study's correction procedure is only directly applicable to NHIS data and may not account for all biases in BMI estimates.
Participant Demographics
Approximately 1.7 million adults aged 18 and over, with stratification by race and sex.
Statistical Information
P-Value
p<0.01
Statistical Significance
p<0.01
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website