The reproducibility of dietary intake data assessed with the cross-check dietary history method

Abstract

The reproducibility of food intake data from elderly men in the Zutphen Study (Zutphen, The Netherlands) was investigated in repeated dietary surveys carried out three (n = 115) and 12 (n = 145) months after the initial survey (April 1985). The differences in the reproducibility estimations for the two different time periods were generally small. The ratios of the interindividual and intraindividual variance were large for carbohydrates (2.6 and 2.7 for three months and 12 months, respectively) and small for vitamin A (1.1 and 0.4 for three months and 12 months, respectively). The larger this ratio, the higher the probability of detecting an existing relation. Information about inter- and intraindividual variation was used to calculate the attenuation factor. For most nutrients, the attenuation factor was about 0.8. This implies that a simple correlation between a nutrient and a risk factor will be only slightly lowered because of measurement error and the temporal variability of the dietary measurement when the cross-check dietary history method is applied once (e.g., a "real" correlation of 0.40 would be expected to be lowered to 0.32).