The variation from day to day, between individuals and within individuals, in the consumption of energy and a variety of nutrients is presented for two groups of executive grade civil servants aged 40-49, numbering 83 and 68 and working in London in 1970-1971, and for 98 drivers and 83 conductors aged 30-67 of London's double decker buses in 1958-1967, a total of 332 men. Each man weighed and recorded his food for at least a week. The reliability with which these men could be classified into extreme thirds of the distribution of individual consumption of the various 'nutrients' or foods on the basis of a single day's or of several days' measurement was calculated. The number of days of measurement required to achieve a given reliability of classification into extreme thirds of the distribution was also estimated. The key is the ratio of the 'between-person' to the 'within-person' variance for the particular nutrient. A diagram is presented of how this ratio is related to the number of days of survey required for a given reliability. Nutrients fall into three main groups--those consumed in relatively large amounts each day (eg protein, fat), those found in moderate amounts in many or most foods but in very large quantities in a few foods (eg dietary cholesterol, calcium), and those which may not be consumed at all by some people but are taken in large quantities by others (eg alcohol). The number of days of survey required for 80 per cent reliable classification of individuals varies from 2 or 3 days for some nutrients like sugar or total carbohydrates to 2 or 3 weeks for others like dietary cholesterol or the ratio of polyunsaturated fatty acids to saturated fatty acids. One day's survey classified no nutrients with 80 per cent reliability in our data, whereas one week's survey classified most nutrients with this reliability or better, although for a few the figure is lower. The precision of a week's survey is also shown in absolute quantities such as grams as distinct from thirds of the distribution. The relevance of these observations to the use of the results of 24-hour surveys in population surveys and correlation and regression analysis is discussed.