Learn More about Day-of-Week Effect

Dietary intakes often vary by the day of the week. In particular, intakes of many foods and beverages, and thus energy intakes and macronutrient distribution, tend to be different on weekends than on weekdays (Monday through Thursday). For [glossary term:] short-term instruments (e.g., 24-hour dietary recalls [24HR] and food records) that capture intake for a given day or a small number of days, this [glossary term:] day-of-week effect could be problematic in the analysis of a research question of interest, for example, if one is interested in estimating a population's [glossary term:] usual dietary intake (see 24-hour Dietary Recall Profile and Food Record Profile).

Day-of-week and other [glossary term:] nuisance effects can be minimized through both study design and analysis procedures. When collecting a single day of intake using a 24HR or food record, respondents could be randomly assigned to weekend or weekday strata, with 3/7 of the sample completing weekend reports (Friday, Saturday and Sunday) and 4/7 completing weekday reports (Monday through Thursday). When collecting multiple days of data for each respondent, collecting information for both weekdays and weekends across the sample is beneficial.

Regardless of the study design employed to minimize the day–of-week effect, day-of-week can be added as a [glossary term:] covariate in the analysis to further minimize its effect.

For More Information

Thompson FE, Larkin FA, Brown MB. Weekend-weekday differences in reported dietary intake: The Nationwide Food Consumption Survey, 1977-78. Nutr Res 1986;6:647-62.