A Warning About Using Predicted Values From Regression Models for Epidemiologic Inquiry.
- Author(s): Ogburn, Elizabeth L
- Rudolph, Kara E
- Morello-Frosch, Rachel
- Khan, Amber
- Casey, Joan A
- et al.
Published Web Locationhttps://doi.org/10.1093/aje/kwaa282
In many settings researchers may not have direct access to data on one or more variables needed for an analysis, and instead may use regression-based estimates of those variables. Using such estimates in place of original data, however, introduces complications and can result in uninterpretable analyses. In simulations and observational data we illustrate the issues that arise when an average treatment effect is estimated from data where the outcome of interest is a prediction from an auxiliary model. We show that bias in any direction can result, both under the null and alternative hypotheses.