Relative validity and reproducibility of a French dietary history questionnaire

Background. A self-administered dietary history questionnaire, especially developed for use in a large French prospective cohort study, was tested for accuracy of food intake measurement by comparing it to the average of 9-12 24-hour recalls. This questionnaire was structured according to the French meal pattern. An important feature of the questionnaire was the separation into a quantification part and qualification part. The first part quantifies consumption by frequency and portion sizes per food group or food item. The second part provides more detailed qualitative information on separate items within one food group. The total number of food items in the questionnaire was 238. Methods. The questionnaire was administered twice to 119 study subjects, with an interval of approximately one year (1990-1991). During that year, 24-hour recalls were carried out monthly. Reproducibility and relative validity of the questionnaire were assessed. Results. The correlation coefficients for reproducibility ranged from 0.40 to 0.74 for foods and from 0.54 to 0.75 for nutrients. The correlation coefficients for relative validity ranged from 0.10 to 0.71 for foods and from 0.29 to 0.81 for nutrients (adjustment for total energy and attenuation for nutrients). Percentage of subjects classified in the same or adjacent quintile by questionnaire as well as by 24-hour recall was on average 76% for foods and 72% for nutrients. Conclusions. These data indicate that this questionnaire can be used to classify study subjects according to their food or nutrient intake over a one-year period, within a known degree of precision.