Table 4 Comparison of methods for handling measurement error in a real dataset using a repeat FFQ on a 33% sub-sample, with total energy intake as potential confounder.
From: The impact of imprecisely measured covariates on estimating gene-environment interactions
| Â | Without adjustment for total energy intake | With adjustment for total energy intake | With adjustment for total energy intake | ||
|---|---|---|---|---|---|
| Â | Ignoring all measurement error | Regression calibration | Ignoring measurement error | Regression calibration assuming energy intake perfectly measured | Regression calibration allowing for measurement error in energy intake |
0 (se) | 3.69 (.02) | 3.64 (.02) | 4.04 (.05) | 4.00 (.05) | 4.19 (.08) |
1 (se) | .48 (.20) | .38 (.32) | .42 (.20) | .32 (.32) | .32 (.33) |
2 (se) | .41 (.03) | .51 (.04) | .45 (.03) | .56 (.04) | .57 (.04) |
3 (se) | .88 (.27) | 1.04 (.40) | .95 (.27) | 1.12 (.39) | 1.14 (.39) |
4 (se) (× 1000) | - | - | -.15 (.02) | -.16 (.02) | -.24 (.03) |